# Climate / Weather / Ocean Modeling

Climate, weather, and ocean modeling and simulation using computational and AI-based methods.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## OceanCoder: A Verification-Guided Large Language Model for Automated Simulation Modelling in Ocean Engineering

DevFeed: [OceanCoder: A Verification-Guided Large Language Model for Automated Simulation Modelling in Ocean Engineering](<https://devfeed.tech/articles/oceancoder-a-verification-guided-large-language-model-for-automated-simulation-modelling-in-ocean-engineering-145165.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26333>)

Author: Can Xue, Changhong He, Ziyi Sun, Anliang Ge, Shimin Yu, Bingchen Liang

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [qwen](<https://devfeed.tech/topics/qwen.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [modelling](<https://devfeed.tech/tags/modelling.md>), [programming](<https://devfeed.tech/tags/programming.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

OceanCoder uses engineering verification as a training signal for automated ocean simulation modelling: successful code execution alone does not show that a model or its results meet engineering requirements. Built on Qwen3-8B, it is trained on 12,000 verified examples across 12 task categories, then guided by graded rewards from checks of inputs and constraints, completion of required analyses, and plausibility of computed outputs. The paper reports Pass@1 rising from 0% for the base model to 46.77% after supervised fine-tuning and 51.43% after group relative policy optimisation, outperforming the compared base models and closed-source system. Its benchmark includes out-of-distribution tasks and real-world engineering cases; the supplied text does not specify the comparison system or broader deployment limitations.

### Source excerpt

arXiv:2611.26333v1 Announce Type: new Abstract: Numerical simulation is important in ocean engineering, but model construction requires expert knowledge. Large language models support automated modelling, but code syntax and successful execution alone do not establish whether generated models and results meet engineering requirements. We present OceanCoder, a Qwen3-8B-based large language model for automated simulation modelling in ocean engineering. To address specialised programming requirements and scarce training data, we develop an extensible data construction pipeline producing 12,000 verified supervised fine-tuning (SFT) examples across 12 engineering task categories. A three-layer verification framework checks model inputs against engineering parameters and task constraints, verifies completion of required simulation analyses, and assesses the engineering plausibility of computed outputs. Its outcomes provide graded rewards for group relative policy optimisation (GRPO), guiding the model towards engineering task completion. We also construct the first benchmark for automated modelling in ocean engineering, covering out-of-distribution tasks and real-world engineering cases. Experiments and ablation studies demonstrate the effectiveness of the data pipeline, verification framework and reward design. OceanCoder outperforms both base models and the closed-source comparison, with Pass@1 increasing from 0% for the base model to 46.77% after SFT and 51.43% after GRPO. These results support engineering verification as a training signal for automated simulation modelling.

## Reinforcement-Aligned Probabilistic Weather Forecasting with Discrete Tokens

DevFeed: [Reinforcement-Aligned Probabilistic Weather Forecasting with Discrete Tokens](<https://devfeed.tech/articles/reinforcement-aligned-probabilistic-weather-forecasting-with-discrete-tokens-145071.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25570>)

Author: Jinhan Li, Zhisheng Chen, Yuxuan Li, Yuan Gao, Fan Xu, Hao Wu, Jinlong Du, Kun Wang

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [caching](<https://devfeed.tech/tags/caching.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [group-relative-policy-optimization](<https://devfeed.tech/tags/group-relative-policy-optimization.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [scale](<https://devfeed.tech/tags/scale.md>), [simulations](<https://devfeed.tech/tags/simulations.md>), [skill](<https://devfeed.tech/tags/skill.md>), [temperature](<https://devfeed.tech/tags/temperature.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [weather](<https://devfeed.tech/tags/weather.md>), [weather-forecasting](<https://devfeed.tech/tags/weather-forecasting.md>)

### AI overview

WeatherCraft uses coarse-to-fine discrete weather tokens and a Transformer that predicts tokens in parallel within each scale to generate probabilistic medium-range forecasts. Exact token log-probabilities let Group Relative Policy Optimization optimize downstream rewards without differentiating through evaluators or coupled models. On ERA5, its eight-member ensemble mean reduced day-15 normalized RMSE by 17.6% versus the strongest evaluated deterministic baseline; with KV caching, inference was about 18x faster than GenCast. The abstract reports improved ensemble skill from direct fair-CRPS adaptation and better forecasts of persistent land-temperature and coupled ocean-temperature extremes from reward-based post-training. These are abstract-level results; details of evaluation and broader performance are not provided.

### Source excerpt

arXiv:2611.25570v1 Announce Type: new Abstract: Global medium-range weather forecasting must not only generate ensembles efficiently to characterize uncertainty in future states, but also serve downstream applications such as extreme-event warnings and cross-sphere coupled simulations. We introduce WeatherCraft, a framework that unifies probabilistic generation and reinforcement learning alignment through discrete weather tokens, bringing the GPT-style pretraining--post-training paradigm to global medium-range weather forecasting. A multiscale tokenizer represents atmospheric states as a coarse-to-fine token hierarchy, while a Transformer models causal dependencies across time and scale and predicts tokens within each scale in parallel. Direct sampling generates diverse ensembles, and exact token log-probabilities enable Group Relative Policy Optimization (GRPO) to maximize downstream task rewards without differentiating through evaluators or coupled models. On the ERA5 benchmark, WeatherCraft's eight-member ensemble mean reduces day-15 normalized RMSE by 17.6% relative to the strongest evaluated deterministic baseline and, with KV caching, achieves an approximately $18\times$ inference speedup over GenCast. Direct fair-CRPS adaptation improves ensemble probabilistic skill, while reward-based post-training improves forecasts of persistent land temperature extremes and coupled ocean heat extremes. This work establishes discrete autoregressive modeling as a general foundation for scalable, task-alignable Earth system foundation models.

## Auditing Learned Dynamics in Weather Models

DevFeed: [Auditing Learned Dynamics in Weather Models](<https://devfeed.tech/articles/auditing-learned-dynamics-in-weather-models-145011.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25119>)

Author: Skylar Gu, Christina Last

Published: 2026-11-20T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [ai](<https://devfeed.tech/tags/ai.md>), [also](<https://devfeed.tech/tags/also.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [association](<https://devfeed.tech/tags/association.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [can](<https://devfeed.tech/tags/can.md>), [central](<https://devfeed.tech/tags/central.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deepmind](<https://devfeed.tech/tags/deepmind.md>), [error](<https://devfeed.tech/tags/error.md>), [event](<https://devfeed.tech/tags/event.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [fall](<https://devfeed.tech/tags/fall.md>), [feature](<https://devfeed.tech/tags/feature.md>), [features](<https://devfeed.tech/tags/features.md>), [models](<https://devfeed.tech/tags/models.md>), [weather](<https://devfeed.tech/tags/weather.md>)

### AI overview

Sparse autoencoder features in GraphCast can have causal effects even without conventional physical meaning, and physically associated features can be steered to alter forecast outcomes. Ablating a feature tied to the model's computational mesh increased global geopotential height error. Suppressing convection- and low-level-vorticity-associated features weakened predicted tropical-cyclone deepening; amplifying them reduced intensity error. Scaling convection features yielded a median 51% error reduction across seven storms. The abstract presents these features as experimental coordinates for auditing and intervening on learned weather dynamics; the evidence provided is an abstract, not the full paper.

### Source excerpt

arXiv:2611.25119v1 Announce Type: new Abstract: Learned weather models are experimentally accessible computational systems whose internal representations can be inspected and manipulated. Using sparse autoencoder features from GraphCast, DeepMind's autoregressive weather forecasting model, we test whether causal relevance requires physical semantics, a question that matters for auditing whether AI forecasters used in high-assurance settings rely on reliable mechanisms. We also look at whether physically associated latent directions can be steered to improve extreme-event forecasts, where interventions are applied to the model's internal activations during the rollout. We find that ablating a feature locked to GraphCast's computational mesh increases global geopotential height error despite lacking conventional physical semantics. Second, suppressing convection- and low-level-vorticity-associated features weakens predicted tropical-cyclone deepening (the fall in central pressure during intensification), while amplifying them reduces intensity error, with amplification of convection features through feature scaling achieving a median of 51\% error reduction over seven storms. Together, these results separate interpretable, physical association from causal utility and establish sparse features as experimental coordinates for auditing and intervening on learned weather dynamics.

## Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior

DevFeed: [Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior](<https://devfeed.tech/articles/xaurora-generative-weather-forecasting-with-denoising-stochastic-interpolants-from-a-foundation-model-prior-144958.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.06509>)

Author: Eliot Walt, Miltiadis Kofinas, Nikolaj M\\"ucke, Efstratios Gavves, Dim Coumou

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>)

Tags: [buffer](<https://devfeed.tech/tags/buffer.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [extreme-weather](<https://devfeed.tech/tags/extreme-weather.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [generative](<https://devfeed.tech/tags/generative.md>), [global](<https://devfeed.tech/tags/global.md>), [has](<https://devfeed.tech/tags/has.md>), [large](<https://devfeed.tech/tags/large.md>), [novel](<https://devfeed.tech/tags/novel.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [physics-ao-ph](<https://devfeed.tech/tags/physics-ao-ph.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [range](<https://devfeed.tech/tags/range.md>), [sample](<https://devfeed.tech/tags/sample.md>), [sde](<https://devfeed.tech/tags/sde.md>), [skill](<https://devfeed.tech/tags/skill.md>), [small](<https://devfeed.tech/tags/small.md>), [train](<https://devfeed.tech/tags/train.md>), [uncertainty-quantification](<https://devfeed.tech/tags/uncertainty-quantification.md>), [weather](<https://devfeed.tech/tags/weather.md>), [weather-forecasting](<https://devfeed.tech/tags/weather-forecasting.md>)

### AI overview

Xaurora extends the pretrained Aurora weather foundation model into a stochastic ensemble forecaster, addressing deterministic forecasts' limits for uncertainty estimates and the cost of training a model from scratch. It is finetuned from Aurora's small version using Denoising Stochastic Interpolants and a replay buffer for Stochastic Differential Equation rollouts, which the abstract says enables probabilistic trajectory training. The authors report that Xaurora approaches state of the art on global ensemble metrics, is competitive with Aurora's large version, and produces skilful 15-day forecasts in seven minutes. The abstract characterizes the method as parameter- and sample-efficient; it provides no further evaluation details here.

### Source excerpt

arXiv:2610.06509v2 Announce Type: replace Abstract: Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill for a fraction of the computational costs of classic physics-based models. However, most existing foundation models are deterministic, limiting the generation of large ensembles for accurate uncertainty quantification, extreme weather risk assessment, and long-range weather forecasting. Furthermore, these models incur a large, often prohibitive, computational overhead to train from scratch. To address these shortcomings, we turn a pretrained deterministic prior model, namely the Aurora foundation model, into a generative ensemble-prediction model. To that end, we introduce a novel generative method, Denoising Stochastic Interpolants, combined with a replay buffer for Stochastic Differential Equation (SDE) rollout, enabling probabilistic training of SDE trajectories. Our stochastic foundation model, Xaurora, is finetuned from the small Aurora version, yet it approaches the state-of-the-art on global ensemble metrics and is competitive with the large version of Aurora. Our method is parameter and sample efficient, and generates skilful 15-day forecasts in 7 minutes. Our results demonstrate that deterministic foundation models can be efficiently extended into even stronger stochastic models.

## A Differentiable Composite Approximation Framework for Autonomous Underwater Vehicle Maneuvering Modeling from Sea-Trial Data

DevFeed: [A Differentiable Composite Approximation Framework for Autonomous Underwater Vehicle Maneuvering Modeling from Sea-Trial Data](<https://devfeed.tech/articles/a-differentiable-composite-approximation-framework-for-autonomous-underwater-vehicle-maneuvering-modeling-from-sea-trial-data-143276.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.19711>)

Author: Aobo Wang, Aifei Xia, Zihao Wang, Lizhu Hao, Shaorong Xie

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [basis](<https://devfeed.tech/tags/basis.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [effects](<https://devfeed.tech/tags/effects.md>), [field](<https://devfeed.tech/tags/field.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [learning](<https://devfeed.tech/tags/learning.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [models](<https://devfeed.tech/tags/models.md>), [motion](<https://devfeed.tech/tags/motion.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [vehicle](<https://devfeed.tech/tags/vehicle.md>)

### AI overview

The framework jointly calibrates a constrained polynomial basis and a data-adaptive neural residual as one differentiable predictor for AUV maneuvering. Its gradient-based method uses sensitivity-aware bounded polynomial updates while the neural residual captures remaining nonlinear discrepancies. A turning-motion procedure estimates and compensates for ocean currents when forming training and rollout targets. In sea trials with a 7-meter AUV across multiple maneuvering conditions, it improved recursive trajectory and velocity prediction over polynomial-only, neural-only, and frozen-prior hybrid baselines. The evidence provided is an abstract, so implementation details and quantitative results are not available.

### Source excerpt

arXiv:2606.19711v2 Announce Type: replace-cross Abstract: Field-based modeling from onboard measurements can produce autonomous underwater vehicle (AUV) maneuvering models that reflect real operating characteristics. From an approximation perspective, conventional maneuvering models use predefined constraint polynomial bases, whereas data-driven models use data-adaptive bases. Motivated by this basis-function view, this paper presents a differentiable composite approximation formulation, in which the polynomial basis component and the data-adaptive basis component are treated as differentiable parts of a unified predictor and calibrated jointly. A gradient-based co-calibration method is developed for full-scale AUV maneuvering prediction, where a sensitivity-aware mechanism regulates bounded polynomial updates while the neural residual captures remaining nonlinear discrepancies under a shared prediction objective. To account for ocean-current effects in field data, a turning-motion-based current estimation and compensation procedure is incorporated to construct current-compensated learning targets for training and rollout. The framework is evaluated using sea-trial data collected from a 7-meter AUV under multiple maneuvering conditions. Results show that the proposed method improves recursive trajectory and velocity prediction compared with polynomial-only, neural-only, and frozen-prior hybrid baselines, demonstrating its applicability to field-data-based AUV maneuvering modeling.

## Distribution-Free Uncertainty Quantification for Weather Forecasting: Conformal Prediction Under Spatiotemporal Dependence

DevFeed: [Distribution-Free Uncertainty Quantification for Weather Forecasting: Conformal Prediction Under Spatiotemporal Dependence](<https://devfeed.tech/articles/distribution-free-uncertainty-quantification-for-weather-forecasting-conformal-prediction-under-spatiotemporal-dependence-143508.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24329>)

Author: Mariya

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>)

Tags: [conformal-prediction](<https://devfeed.tech/tags/conformal-prediction.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>), [uncertainty-quantification](<https://devfeed.tech/tags/uncertainty-quantification.md>), [weather](<https://devfeed.tech/tags/weather.md>), [weather-forecasting](<https://devfeed.tech/tags/weather-forecasting.md>)

### AI overview

Per-cell conformal methods achieved near-nominal marginal coverage for gridded 2 m temperature forecasts, but coverage varied sharply across days: the variance in the fraction of covered grid cells was about 3-10 times the independent-cell benchmark, and forecast misses clustered over time. The study compared eight interval procedures on ERA5 at 5.625° resolution using a CNN and ECMWF HRES across eight lead times. An oracle adjustment using each day's mean normalized error removed most excess spatial dispersion, suggesting widespread high-error days drive much of it. A day-scale adjustment based on seasonal terms and verified errors reduced overdispersion without wider intervals, but improved interval score by at most 0.6%; no method performed best on both measures. Results are limited to one variable, a coarse grid, a reanalysis target, and two forecasters.

### Source excerpt

arXiv:2611.24329v1 Announce Type: new Abstract: Conformal prediction gives finite-sample, distribution-free marginal coverage and has begun to be applied to gridded weather forecasts. Marginal coverage concerns the long-run fraction of covered points at a location, not how coverage behaves jointly across space and time on a given day. I benchmark eight interval-construction procedures (Gaussian, pooled and per-cell split conformal, per-season, adaptive conformal inference and rolling windows) for gridded 2 m temperature forecasts at eight lead times from 6 hours to 10 days, using ERA5 at 5.625 degree resolution, a deliberately modest convolutional forecaster and ECMWF's operational HRES, with calibration in 2017-2018 and testing in 2019-2021. Alongside coverage, width and interval score, I report dependence diagnostics: a spatial overdispersion index, quantiles of daily spatial coverage and miss persistence relative to a shuffled-days null. Per-cell methods reach near-nominal marginal coverage, yet the day-to-day variance of the fraction of cells covered is roughly 3 to 10 times what independent cells would give, and misses cluster in time; both effects grow with lead time for the CNN, also appear for HRES, and are shared by all methods. An oracle that divides each day's normalised errors by that day's mean removes 81 to 92 percent of the excess dispersion for the CNN and 93 to 98 percent for HRES, so days of large errors across much of the grid account for most of it. A day-scale predicted from seasonal terms and already-verified errors lowers the overdispersion index without widening intervals but improves interval score by at most 0.6 percent; on HRES from 12 hours to 3 days it has the lowest overdispersion index while ACI or season-conditional calibration has the best interval score, so no method is best on both. The study covers one variable, one coarse grid, a reanalysis target and two forecasters.

## Learning Calibrated and Samplable Predictive Distributions of Surface-Ocean $\\Delta p$CO$\_2$ Using Tabular Diffusion Models

DevFeed: [Learning Calibrated and Samplable Predictive Distributions of Surface-Ocean $\\Delta p$CO$\_2$ Using Tabular Diffusion Models](<https://devfeed.tech/articles/learning-calibrated-and-samplable-predictive-distributions-of-surface-ocean-delta-p-co-2-using-tabular-diffusion-models-141674.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21769>)

Author: Gabriele Accarino, Mohammad M. Amirian, Thea H. Heimdal, Amanda R. Fay, Galen A. McKinley, Viviana Acquaviva

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Calibrated uncertainty](<https://devfeed.tech/topics/calibrated-uncertainty.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [generative](<https://devfeed.tech/tags/generative.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [physics-ao-ph](<https://devfeed.tech/tags/physics-ao-ph.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>), [uncertainty-quantification](<https://devfeed.tech/tags/uncertainty-quantification.md>), [xgboost](<https://devfeed.tech/tags/xgboost.md>)

### AI overview

Treeffuser estimates a conditional predictive distribution for sea-air ΔpCO₂ from 13 environmental, spatial and temporal predictors, providing observation-level uncertainty for sparse ocean measurements. On a held-out SOCAT test set, it had the best continuous ranked probability score among the evaluated uncertainty methods (8.229 μatm) and coverage closest to nominal 68% and 95% levels (0.686 and 0.930). Its point-prediction skill was comparable to deterministic XGBoost, with RMSE 18.4 versus 17.7 μatm and R² 0.77 versus 0.79. The abstract says generated samples may support probabilistic analyses; spatially coherent field reconstruction remains future work requiring cross-grid-cell dependence modeling and evaluation on spatially held-out data.

### Source excerpt

arXiv:2611.21769v1 Announce Type: new Abstract: The ocean absorbs almost 30% of anthropogenic CO$_2$ emissions, but quantifying this sink requires estimating surface-ocean CO$_2$ from observations that are sparse in space and time. Most existing machine-learning estimates of this field are deterministic, giving a single value per grid point, with uncertainty approximated post hoc via residuals, ensembles, or prescribed distributions. We instead learn a conditional predictive distribution for each observation: using Treeffuser, a conditional diffusion model with gradient-boosted-tree score functions, we estimate the full predictive distribution of $\Delta p$CO$_2$ (the sea-air $p$CO$_2$ difference) from 13 environmental, spatial, and temporal predictors. On a held-out SOCAT test set, Treeffuser attains the lowest continuous ranked probability score among the uncertainty-quantification methods evaluated (8.229 $\mu$atm) and the coverage closest to the nominal 68% / 95% levels (0.686 / 0.930), while retaining point-prediction skill comparable to a deterministic XGBoost baseline (RMSE 18.4 vs. 17.7 $\mu$atm; $R^2$ 0.77 vs. 0.79). These results show that conditional diffusion can provide well-calibrated, observation-level uncertainties while largely preserving point-prediction skill. Because Treeffuser is generative, its samples can support probabilistic analyses of $\Delta p$CO$_2$; extending this to spatially coherent field reconstruction will require modeling dependence across grid cells and evaluation on spatially held-out data.

## An AI-Based OSSE Framework to Evaluate Learned Physical Consistency: A Multi-Model Study Using FourCastNet, Aurora, Prithvi WxC, and GraphCast

DevFeed: [An AI-Based OSSE Framework to Evaluate Learned Physical Consistency: A Multi-Model Study Using FourCastNet, Aurora, Prithvi WxC, and GraphCast](<https://devfeed.tech/articles/an-ai-based-osse-framework-to-evaluate-learned-physical-consistency-a-multi-model-study-using-fourcastnet-aurora-prithvi-wxc-and-graphcast-141721.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22024>)

Author: Yash Diggikar, Milton Halem, Aishwarya Raman

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [after](<https://devfeed.tech/tags/after.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [all](<https://devfeed.tech/tags/all.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [can](<https://devfeed.tech/tags/can.md>), [capture](<https://devfeed.tech/tags/capture.md>), [central](<https://devfeed.tech/tags/central.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [example](<https://devfeed.tech/tags/example.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [model](<https://devfeed.tech/tags/model.md>), [study](<https://devfeed.tech/tags/study.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

The framework tests whether four AI weather models reproduce atmospheric responses to inserted observations in OSSE-style forecasts. FourCastNet V2, GraphCast, Aurora, and Prithvi WxC were run autoregressively for 60 days with a 30-day spin-up; ERA5 temperature or wind fields were then inserted, and responses were assessed over a 30-day assimilation cycle. Models respond differently to the same insertions: Aurora and Prithvi WxC show the strongest impacts, while GraphCast is weakest. Three of the four capture the temperature-to-geopotential-height response, and the two foundation models retain a positive tropical 500-hPa zonal-wind response to temperature insertion. Results can also vary among insertion experiments within an architecture. In GraphCast's full 37-level setup, temperature insertion triggers runaway feedback near the upper levels; the abstract reports this can be corrected by excluding levels at or below 100 hPa.

### Source excerpt

arXiv:2611.22024v1 Announce Type: new Abstract: Observing System Simulation Experiments (OSSEs) are a central methodology for evaluating future atmospheric observing systems. We present the first AI-based OSSE framework to test whether different AI weather models can reproduce comparable physical impact from new observations that traditional physics based models generate. We evaluate four distinct architectural AI models on the Charney conjecture that incomplete historical observations can infer the present state of the atmospheric. We considner- FourCastNet V2, GraphCast, Aurora and Prithvi WxC and integrate each autoregressively over a 60-day forecast horizon. After a 30-day spin-up, we insert ERA5 temperature fields to infer winds and related atmospheric fields. Similar OSSE experiments are conducted for wind insertion. We measure the performance of each model's response to observational information on a 30-day data assimilation cycle forecast with and without data insertion. Distinct architectural AI weather models respond differently to the same OSSE observations. Foundation models (i.e. Prithvi WxC and Aurora), produce the strongest impact. For example, while GraphCast is the weakest, all three of the four models capture the temperature-to-geopotential height response. The two foundational models retain a positive, non-trivial, tropical zonal wind at 500 hPa response to temperature insertion. Various data insertion experiments can vary significantly even within a given architecture. We identify an architecture-specific numerical instability in GraphCast's full 37-level configuration that produces a runaway feedback concentrated at the uppermost levels with ERA5 temperature insertion correctable by excluding levels at or below 100 hPa.

## AEGIS: Differentiable Mars Climate Model with Neural Closures

DevFeed: [AEGIS: Differentiable Mars Climate Model with Neural Closures](<https://devfeed.tech/articles/aegis-differentiable-mars-climate-model-with-neural-closures-139831.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.04081>)

Author: Sameera S Kashyap, Victor Cruz, Angel Yepez, Razvan Marinescu

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Fortran](<https://devfeed.tech/topics/fortran.md>)

Tags: [astro-ph-ep](<https://devfeed.tech/tags/astro-ph-ep.md>), [astro-ph-im](<https://devfeed.tech/tags/astro-ph-im.md>), [atmosphere](<https://devfeed.tech/tags/atmosphere.md>), [climate](<https://devfeed.tech/tags/climate.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dust](<https://devfeed.tech/tags/dust.md>), [framework](<https://devfeed.tech/tags/framework.md>), [interfaces](<https://devfeed.tech/tags/interfaces.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mars](<https://devfeed.tech/tags/mars.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [modular](<https://devfeed.tech/tags/modular.md>), [neural](<https://devfeed.tech/tags/neural.md>), [physics](<https://devfeed.tech/tags/physics.md>), [surface](<https://devfeed.tech/tags/surface.md>), [temperature](<https://devfeed.tech/tags/temperature.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

AEGIS is a modular, differentiable Mars climate model that couples Mars atmospheric physics to the Dinosaur dynamical core and provides interfaces for neural closures. The abstract reports stable ten-Mars-year simulations that reproduce the seasonal CO₂ cycle while conserving total CO₂ inventory, capture large-scale surface-temperature structure, and yield surface pressure following MOLA topography. Its coupled-trajectory gradients agree with finite differences, supporting physical calibration and neural training. The authors contrast this differentiable framework with mature Mars GCMs implemented in legacy Fortran, which do not expose gradients; they also highlight computational efficiency, without giving comparative measurements in the supplied text.

### Source excerpt

arXiv:2610.04081v2 Announce Type: replace-cross Abstract: General circulation models (GCMs) are the primary tool for simulating planetary atmospheres. They play a vital role in understanding Mars's atmosphere, as forecasting its unique weather is mission-critical for operations such as entry, descent, and landing. Mars poses unusual challenges for these models, as observations are sparse compared to Earth. In addition, a thin $CO_2$ atmosphere alongside a radiatively active dust cycle creates a volatile atmosphere with large diurnal temperature swings and no true terrestrial analog for validation. Existing Mars GCMs, including the LMD PCM, the NASA Ames Mars GCM, and PlanetWRF, are mature and physically detailed but are implemented in legacy Fortran with finite-difference or finite-volume solvers, and they do not expose gradients for calibration or machine learning. Here we present AEGIS, a modular differentiable Mars climate model that couples Mars's unique atmospheric physics to the Dinosaur dynamical core, with interfaces for neural closures. We showcase stable ten-Mars-year simulations that reproduce the seasonal $CO_2$ cycle while conserving the total $CO_2$ inventory, capture realistic large-scale surface-temperature structure, and produce surface pressure that follows Mars Orbiter Laser Altimeter (MOLA) topography. Gradients through coupled trajectories agree with finite differences and support physical calibration and neural training. We compare with conventional GCMs, highlighting the framework's computational efficiency and differentiability.

## Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction

DevFeed: [Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction](<https://devfeed.tech/articles/adversarial-attacks-on-downstream-weather-forecasting-models-application-to-tropical-cyclone-trajectory-prediction-135650.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2510.10140>)

Author: Yue Deng, Francisco Santos, Pang-Ning Tan, Lifeng Luo

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [weather-forecasting](<https://devfeed.tech/tags/weather-forecasting.md>)

### AI overview

Cyc-Attack perturbs deep-learning weather forecasts to steer downstream tropical cyclone trajectory predictions toward target paths. Because standard cyclone detectors are opaque and non-differentiable, the method uses a differentiable surrogate to enable gradient-based attacks. It addresses rare cyclone events with a skewness-aware loss and kernel dilation, and uses distance-based gradient weighting and regularization to limit unrealistic paths. The abstract reports higher target-trajectory true positive rates, lower false alarm rates, and stealthier perturbations than conventional attack methods. It also says Cyc-Attack's adversarial forecasts can guide training an end-to-end model to learn inputs that induce target trajectories.

### Source excerpt

arXiv:2510.10140v3 Announce Type: replace Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In this paper, we investigate the vulnerability of these models to adversarial attacks, where subtle perturbations to upstream forecasts can alter downstream TC trajectory predictions. Crafting perturbed inputs to steer downstream outputs toward attacker-specified trajectories is a challenging problem for several reasons. First, conventional TC detection systems are opaque, non-differentiable black boxes, making standard gradient-based attacks infeasible. Second, the extreme rarity of TC events leads to a severe class imbalance problem, making it difficult to develop attack methods that produce realistic-looking cyclone paths aligned with target trajectories. To overcome these limitations, we propose Cyc-Attack, a novel method for perturbing the forecasts of DLWF models to generate adversarial trajectories. The proposed method uses a differentiable surrogate model to approximate the TC detector's output, enabling the application of gradient-based attacks. Cyc-Attack also employs a skewness-aware loss function with a kernel dilation strategy to address the severe class imbalance problem. Distance-based gradient weighting and regularization strategies are also introduced to constrain perturbations to eliminate unrealistic-looking TC paths. Our experiments show that Cyc-Attack achieves a higher true positive rate in matching the target trajectories, along with lower false alarm rates and stealthier perturbations than conventional attack methods. We further demonstrate that the adversarial upstream forecasts generated by Cyc-Attack can be leveraged as initial guidance to train an end-to-end model for learning adversarial input samples that would induce target trajectories.

## Climate Temporal Temperature Prediction via an Adaptive Stacked Bidirectional Residual Mamba Network

DevFeed: [Climate Temporal Temperature Prediction via an Adaptive Stacked Bidirectional Residual Mamba Network](<https://devfeed.tech/articles/climate-temporal-temperature-prediction-via-an-adaptive-stacked-bidirectional-residual-mamba-network-133110.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16322>)

Author: Yongxiang Lei

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Mamba](<https://devfeed.tech/topics/mamba.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [attention](<https://devfeed.tech/tags/attention.md>), [climate](<https://devfeed.tech/tags/climate.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [framework](<https://devfeed.tech/tags/framework.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [implement](<https://devfeed.tech/tags/implement.md>), [inference](<https://devfeed.tech/tags/inference.md>), [mamba](<https://devfeed.tech/tags/mamba.md>), [mlp](<https://devfeed.tech/tags/mlp.md>), [models](<https://devfeed.tech/tags/models.md>), [network](<https://devfeed.tech/tags/network.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [temperature](<https://devfeed.tech/tags/temperature.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

Deep DualMamba is a temperature-forecasting model that uses adaptive bidirectional Mamba encoders and a hardware-aware parallel recurrent algorithm. The authors say its selective state-space design avoids attention and MLP layers, has linear complexity with sequence length, and improves inference throughput. They describe theoretical analysis of approximation and convergence, and a forecasting pipeline built with historical data from UK monitoring stations. The abstract provides no quantitative results or detailed comparison with other models.

### Source excerpt

arXiv:2611.16322v1 Announce Type: new Abstract: Accurate temperatures forecasting relies on traditional meteorological parameters that are essential for monitoring weather informatics and guiding forecasting efforts. This study presents Deep DualMamba, a novel deep learning framework for temporal temperature prediction, built upon an enhanced variant of the recently proposed Mamba network. Unlike conventional Transformer-based architectures, which dominate foundation models but suffer from computational inefficiencies on long sequences, Deep DualMamba leverages selective structured state space models (SSMs) to achieve both scalability and performance. We identify a core limitation of prior subquadratic-time models-namely, their inability to perform long-term and robust forecasting and introduce two key innovations. First, we propose an adaptive bidirectional Mamba as encoders to learn complex and efficient features. Second, we develop a hardware-aware, parallel recurrent algorithm to compensate for the loss of convolutional efficiency, ensuring practical viability at scale. Last, the Deep DualMamba's approximation ability and convergence is theoretical analyzed. These design choices culminate in a simplified, attention- and MLP-free neural architecture that exhibits linear complexity with sequence length and significantly improved inference throughput. To demonstrate its applicability in climate informatics, we implement a full forecasting pipeline using historical meteorological data from UK monitoring stations.

## New research could lead to faster, trustworthy AI models for climate prediction

DevFeed: [New research could lead to faster, trustworthy AI models for climate prediction](<https://devfeed.tech/articles/new-research-could-lead-to-faster-trustworthy-ai-models-for-climate-prediction-131195.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/new-research-could-lead-faster-trustworthy-ai-models-climate-prediction-1112>)

Author: Adam Zewe | MIT News

Published: 2026-11-12T05:00:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [christopher-womack](<https://devfeed.tech/tags/christopher-womack.md>), [climate](<https://devfeed.tech/tags/climate.md>), [climate-change](<https://devfeed.tech/tags/climate-change.md>), [climate-emulation](<https://devfeed.tech/tags/climate-emulation.md>), [computer-modeling](<https://devfeed.tech/tags/computer-modeling.md>), [data](<https://devfeed.tech/tags/data.md>), [eaps](<https://devfeed.tech/tags/eaps.md>), [earth-and-atmospheric-sciences](<https://devfeed.tech/tags/earth-and-atmospheric-sciences.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [faster](<https://devfeed.tech/tags/faster.md>), [idss](<https://devfeed.tech/tags/idss.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mit](<https://devfeed.tech/tags/mit.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [models](<https://devfeed.tech/tags/models.md>), [noelle-selin](<https://devfeed.tech/tags/noelle-selin.md>), [pollution](<https://devfeed.tech/tags/pollution.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [public-health](<https://devfeed.tech/tags/public-health.md>), [research](<https://devfeed.tech/tags/research.md>), [school-of-science](<https://devfeed.tech/tags/school-of-science.md>), [sustainability](<https://devfeed.tech/tags/sustainability.md>), [training](<https://devfeed.tech/tags/training.md>), [trustworthy-ai](<https://devfeed.tech/tags/trustworthy-ai.md>)

### AI overview

MIT researchers describe a method for training climate emulators with optimized synthetic emissions scenarios. Instead of running a full Earth system model six to eight times to create training data, the method requires one run; an optimization process then adjusts scenarios, including abrupt emissions changes, to reduce emulator error. The researchers report that emulators trained this way used much less data, predicted unfamiliar scenarios more accurately, and captured effects of local pollutant controls that the traditional emulators they evaluated missed. The synthetic training scenarios need not resemble realistic futures. The team says the method could speed emulator production, but plans further tests using scenarios from a full Earth system model and other climate models.

### Source excerpt

MIT scientists developed a training method to generate models that simulate the effects of human activities on climate much more quickly than other approaches.

## HaiRuo: Forecasting Ocean Eddies as Fields and Objects with a Satellite-Altimetry Foundation Model

DevFeed: [HaiRuo: Forecasting Ocean Eddies as Fields and Objects with a Satellite-Altimetry Foundation Model](<https://devfeed.tech/articles/hairuo-forecasting-ocean-eddies-as-fields-and-objects-with-a-satellite-altimetry-foundation-model-128806.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14136>)

Author: Xukun Qin, Haochen Sun, Yuyang Tian, Ge Chen

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [fields](<https://devfeed.tech/tags/fields.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [frame](<https://devfeed.tech/tags/frame.md>), [global](<https://devfeed.tech/tags/global.md>), [masks](<https://devfeed.tech/tags/masks.md>), [object](<https://devfeed.tech/tags/object.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [open](<https://devfeed.tech/tags/open.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [polar](<https://devfeed.tech/tags/polar.md>), [satellite](<https://devfeed.tech/tags/satellite.md>), [skill](<https://devfeed.tech/tags/skill.md>)

### AI overview

HaiRuo forecasts ocean eddies both as physical fields and as tracked objects: from 30 days of satellite sea-level maps, one pass predicts 15 days of sea level, geostrophic velocity, daily eddy masks, and trajectories for current eddies. Its open-weight HaiRuo-1B model was pretrained without labels on 24 years of global satellite altimetry; XuanJi samples forecasts in each eddy's co-moving polar frame and refines paths over three look-ahead rounds. In a pre-registered global evaluation, HaiRuo's 15-day centre error was 25.2 km versus 30.6 km for 14 comparison methods. The abstract also reports improved field and mask scores, lower errors outside labelled regions and across both ENSO phases, and reduced pipeline error when trajectories were passed through a fixed tracker. These are reported study results; the supplied text is an abstract, not a full account of methods or limitations.

### Source excerpt

arXiv:2611.14136v1 Announce Type: new Abstract: Mesoscale eddies carry most of the ocean's kinetic energy and move heat, salt and nutrients across basins, yet where an eddy will be two weeks ahead is still read off ocean models with post-hoc tracking heuristics. We introduce HaiRuo, which forecasts eddies as fields and as objects at once: from 30 days of satellite sea-level maps, one forward pass returns 15 days of sea level and geostrophic velocity, daily eddy masks and the trajectory of every eddy alive today. HaiRuo pairs two components with a clear division of labour: (1) HaiRuo-1B, an open-weight 1.05-billion-parameter foundation model pretrained without labels on 24 years of global satellite-altimetry observations, which supplies the 15-day physical fields and masks (+0.14 field skill and +1.1 mIoU points under the same decoder) and further lowers 15-day centre error by 1.2 km frozen (1.35 km over training from scratch); and (2) XuanJi, a Lagrangian object decoder that samples the evolving forecast in each eddy's co-moving polar frame and refines the 15-day path across three look-ahead rounds, removing 2.5 km on HaiRuo-1B (2.9 km with joint fine-tuning) and 2.5-3.3 km via its object attention across six published backbones. Under one pre-registered global evaluation over the whole ocean, HaiRuo improves on fourteen methods on every endpoint (25.2 vs. 30.6 km 15-day centre error, -18%), holding its margin outside the labelled regions and through both phases of the El Nino-Southern Oscillation (ENSO), while reproducing westward drift, 50-60 deg S eastward reversal and poleward cyclone-anticyclone deflection. Over ten days through one fixed tracker, HaiRuo's forecast field cuts the eddy-centre error of WenHai and XiHe by 37-43% (-2.8 km vs. day 0 while they degrade +4.3-8.7 km), and its object trajectories cut pipeline error by 77-78% globally. Open-weight checkpoints, code and project page: https://github.com/xkqin/HaiRuo

## Opening the datasets behind our AI weather models

DevFeed: [Opening the datasets behind our AI weather models](<https://devfeed.tech/articles/opening-the-datasets-behind-our-ai-weather-models-133528.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/opening-the-datasets-behind-our-ai-weather-models/>)

Author: WeatherNext team

Published: 2026-11-10T11:13:04Z

Content type: release

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [geospatial](<https://devfeed.tech/topics/geospatial.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [applications](<https://devfeed.tech/tags/applications.md>), [climate](<https://devfeed.tech/tags/climate.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [developers](<https://devfeed.tech/tags/developers.md>), [earth](<https://devfeed.tech/tags/earth.md>), [global](<https://devfeed.tech/tags/global.md>), [imagery](<https://devfeed.tech/tags/imagery.md>), [live](<https://devfeed.tech/tags/live.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [models](<https://devfeed.tech/tags/models.md>), [satellite](<https://devfeed.tech/tags/satellite.md>), [satellites](<https://devfeed.tech/tags/satellites.md>), [science](<https://devfeed.tech/tags/science.md>), [train](<https://devfeed.tech/tags/train.md>), [water](<https://devfeed.tech/tags/water.md>), [weather](<https://devfeed.tech/tags/weather.md>)

### AI overview

SatWeave and PARDIG are being released with historical archives and live feeds for researchers and developers building weather, hydrology, and climate applications. SatWeave combines imagery from five geostationary satellites into a global mosaic that gives WeatherNext 3 a live view of clouds and storms. The satellites differ in map projections, file formats, sensors, and scan schedules of 10 to 30 minutes, making a coherent global map difficult; the excerpt says existing composites commonly omit incompatible details, use four or fewer channels, or update only every few hours. PARDIG is an AI-based global precipitation dataset used to train WeatherNext 3 precipitation forecasts.

### Source excerpt

Foundational precipitation and geostationary satellite datasets to observe the planet clearly.

## PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling

DevFeed: [PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling](<https://devfeed.tech/articles/prola-principal-orthogonal-low-rank-adaptation-for-predictive-spatiotemporal-weather-downscaling-125358.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11318>)

Author: Minseo Yoon, Minseong Bae, Sojin Lee, Hyunwoo J. Kim

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [lora](<https://devfeed.tech/topics/lora.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [adapting](<https://devfeed.tech/tags/adapting.md>), [budget](<https://devfeed.tech/tags/budget.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [extend](<https://devfeed.tech/tags/extend.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [future](<https://devfeed.tech/tags/future.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [rank](<https://devfeed.tech/tags/rank.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [updates](<https://devfeed.tech/tags/updates.md>), [weather](<https://devfeed.tech/tags/weather.md>), [weather-prediction](<https://devfeed.tech/tags/weather-prediction.md>)

### AI overview

The paper frames predictive spatiotemporal weather downscaling (PSWD) as jointly refining spatial and temporal resolution while forecasting future high-resolution weather fields from recent coarse states. Its framework separates prediction into spatial and temporal stages, using a shared pretrained backbone, fixed numerical scaffolds, and lightweight residual heads. For adapting the backbone, PROLA divides a fixed low-rank budget between the weights' principal directions and their orthogonal complement, then uses gradient signals to rescale rank-1 optimizer updates without increasing trainable rank. The abstract reports that PROLA outperforms representative low-rank adaptation baselines in PSWD and that experiments on other datasets and tasks support broader applicability; it provides no specific metrics or experimental details.

### Source excerpt

arXiv:2611.11318v1 Announce Type: new Abstract: High-resolution weather prediction is important for resolving local atmospheric patterns missed by coarse global forecasts. Large pretrained weather backbones have improved global forecasting, but adapting them to produce future high-resolution fields from recent coarse states remains challenging and costly. We formulate this setting as Predictive Spatiotemporal Weather Downscaling (PSWD), a task that jointly refines spatial and temporal resolution while predicting future high-resolution trajectories. To this end, we propose a framework that decomposes prediction into spatial and temporal stages using a shared pretrained backbone, fixed numerical scaffolds, and lightweight residual heads. For backbone adaptation, we introduce PROLA (PRincipal-Orthogonal Low-rank Adaptation), which allocates a fixed low-rank budget between pretrained weights' principal directions and their orthogonal complement. PROLA further rescales rank-1 optimizer updates using gradient signals, improving adaptation without increasing trainable rank. Experiments in the PSWD setting show that PROLA outperforms representative low-rank adaptation baselines. Further experiments across diverse datasets and tasks support the broader applicability of PROLA, showing that its benefits extend beyond the primary weather downscaling setting.

## Rescene-ESM: an Earth system model built around a frozen AI weather model

DevFeed: [Rescene-ESM: an Earth system model built around a frozen AI weather model](<https://devfeed.tech/articles/rescene-esm-an-earth-system-model-built-around-a-frozen-ai-weather-model-125315.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11066>)

Author: Minjong Cheon, Kaoru Kakinuma

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [atmosphere](<https://devfeed.tech/tags/atmosphere.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [climate](<https://devfeed.tech/tags/climate.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [earth](<https://devfeed.tech/tags/earth.md>), [energy](<https://devfeed.tech/tags/energy.md>), [esm](<https://devfeed.tech/tags/esm.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-ao-ph](<https://devfeed.tech/tags/physics-ao-ph.md>), [system](<https://devfeed.tech/tags/system.md>), [weather](<https://devfeed.tech/tags/weather.md>)

### AI overview

Rescene-ESM couples a frozen 20.8-million-parameter AI weather model with observation-constrained physical ocean, sea-ice, land, river, carbon and energy components through YAHO. The AI atmosphere alone produces only about one-third of observed year-to-year ocean variability; adding an interactive mixed layer, equatorial wave ocean, stochastic forcing from the observed SST-equation residual, and land moisture flux builds El Niño variability and teleconnections while leaving mean climate almost unchanged. The model runs about 1,000 simulated years per day on one GPU and maintains observed climate for 1,000 years without drift. The abstract also reports reproduction of 1979-2022 global warming, a transient climate response of 1.60 K, and runoff routing to 212 gauges with median seasonal-cycle correlation 0.79. For 2081-2100, heatwave exposure differs by a factor of 4.7 between SSP1 and SSP3, with three-quarters of the difference attributed to the warmer climate.

### Source excerpt

arXiv:2611.11066v1 Announce Type: cross Abstract: Earth system models underpin climate projections, but their cost limits how many scenarios, ensemble members and impact pathways can be explored. Machine-learning weather models forecast as skillfully as physics-based models at a fraction of the cost, yet coupled to an ocean they have produced weak El Nino variability or have learned it from climate-model output, and none carries the climate through rivers to the people exposed to it. Here we present Rescene-ESM, an Earth system model whose coupler, YAHO, yokes a frozen 20.8-million-parameter AI weather model to physically formulated ocean, sea-ice, land, river, carbon and energy components constrained by observations. Adding the couplings one at a time shows what each contributes: over a climatological ocean the AI atmosphere varies from year to year by a third of the observed amount over the oceans, and an interactive mixed layer, an equatorial wave ocean, the residual of the observed sea surface temperature (SST) equation as stochastic forcing and the land's moisture flux raise this step by step and bring El Nino and its teleconnections, leaving the mean climate almost unchanged. The full model simulates about 1,000 years per day on one graphics processing unit, holds the observed climate for a thousand years without drift, reproduces the observed 1979-2022 global warming, carries forced change with a physically based structure around the frozen network (transient climate response 1.60 K), routes runoff to 212 river gauges with a median seasonal-cycle correlation of 0.79 and, driven by emissions, separates the heatwave exposure of an SSP1 and an SSP3 world by a factor of 4.7 in 2081-2100, three-quarters of it through the warmer climate.

## Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting

DevFeed: [Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting](<https://devfeed.tech/articles/tyche-one-step-flow-for-efficient-probabilistic-weather-forecasting-123132.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.06916>)

Author: Fan Xu, Yuan Gao, Kun Wang, Rui Su, Fenghua Ling, Hao Wu, Wanli Ouyang

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Data science and engineering](<https://devfeed.tech/topics/data-science-and-engineering.md>)

Tags: [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [ecmwf](<https://devfeed.tech/tags/ecmwf.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [flow](<https://devfeed.tech/tags/flow.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [function](<https://devfeed.tech/tags/function.md>), [future](<https://devfeed.tech/tags/future.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [generative](<https://devfeed.tech/tags/generative.md>), [global](<https://devfeed.tech/tags/global.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model](<https://devfeed.tech/tags/model.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [weather](<https://devfeed.tech/tags/weather.md>), [weather-forecasting](<https://devfeed.tech/tags/weather-forecasting.md>)

### AI overview

Tyche is a probabilistic weather forecaster that maps Gaussian noise directly to future weather states in one function evaluation, avoiding the repeated denoising steps used by multi-step generative forecasts. It uses a destination-aware average-velocity flow, a Jacobian-vector-product-regularized rectification objective for temporal self-consistency, and an isotropic Swin-style transformer for global weather fields. A rollout-based finetuning stage with curriculum CRPS supervision targets ensemble reliability during autoregressive forecasts. On ERA5 at 1.5° resolution and six-hour intervals, the authors report that Tyche's single-evaluation forecasts match or exceed the skill and calibration of state-of-the-art multi-step generative baselines and the operational ECMWF IFS ensemble.

### Source excerpt

arXiv:2605.06916v2 Announce Type: replace Abstract: Probabilistic weather forecasting requires not only accurate trajectories, but calibrated distributions over plausible atmospheric futures. Recent data-driven systems have achieved remarkable deterministic skill, and diffusion-based ensemble forecasters have substantially improved sample realism and uncertainty quantification. However, their inference cost scales with forecast horizon, ensemble size, and the number of denoising steps required for each transition, making large operational ensembles expensive. To address this, we present Tyche, a one-step conditional flow model for efficient probabilistic weather forecasting. Tyche models the conditional forecast distribution with a destination-aware average-velocity flow that maps Gaussian noise directly to future weather states in a single function evaluation (1-NFE). To make this one-step transport learnable in high-dimensional geophysical fields, we derive a JVP-regularized rectification objective that enforces temporal self-consistency across source and destination flow timesteps without explicitly forming Jacobians. The transport field is parameterized by an isotropic Swin-style transformer that preserves fine-scale spatial structure while remaining scalable on global grids. To improve ensemble reliability under autoregressive forecasting, we further introduce a rollout-based finetuning stage with curriculum CRPS calibration supervision. Experiments on ERA5 at 1.5$^\circ$ and 6-hour resolution show that our Tyche, using merely a single NFE, matches or exceeds the forecast skill and calibration of state-of-the-art multi-step generative baselines and the operational ECMWF IFS ensemble.

## Stable probabilistic emulation of partially observed dynamical systems

DevFeed: [Stable probabilistic emulation of partially observed dynamical systems](<https://devfeed.tech/articles/stable-probabilistic-emulation-of-partially-observed-dynamical-systems-123394.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09317>)

Author: Mario Massy, Sara Shamekh, Fabrizio Falasca, Matthieu Blanke

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [emulation](<https://devfeed.tech/tags/emulation.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [stable](<https://devfeed.tech/tags/stable.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The paper introduces forced-dissipative stochastic interpolants for learning stochastic reduced dynamics in partially observed systems. The architecture imposes structural constraints inspired by turbulent dynamics to provide stability while retaining flexibility to model probabilistic behavior. The authors establish a Foster-Lyapunov drift condition, prove geometric ergodicity, and show stability under steady external forcing. On the two-timescale Lorenz-96 system, the emulator remains stable over long integrations and finite-amplitude forcing, and accurately predicts forced responses in both mean and variance. Evidence here is limited to the abstract.

### Source excerpt

arXiv:2611.09317v1 Announce Type: new Abstract: Predicting the long-term behavior of partially observed dynamical systems such as the coupled atmosphere-ocean system is central to societal decision-making. Motivated by the success of deep learning emulators in weather forecasting, data-driven climate models represent a promising approach. However, climate emulation poses distinct challenges: models must account for unresolved fast variables introduced by unavoidable coarse-graining, reproduce long-term statistics, and remain stable over arbitrarily long rollouts and under external perturbations. These requirements motivate stochastic data-driven emulators, but modern generative models lack stability guarantees. We introduce forced-dissipative stochastic interpolants, a generative framework for learning stochastic reduced dynamics. Its architecture uses structural constraints inspired by turbulent dynamics, which provide stability by design while retaining the flexibility of stochastic interpolants to represent complex probabilistic dynamics. Building on the theory of Markov-chain stability, we establish a Foster--Lyapunov drift condition and prove geometric ergodicity for our emulator, together with stability under steady external forcing. We evaluate the framework on the two-timescale Lorenz-96 system, a prototype of partially observed multiscale turbulence. The resulting emulator remains stable over long integrations and under finite-amplitude forcing, with accurate prediction of forced responses of both the mean and variance.

## Distinguishing Initial-Condition and Model Error Using Machine-Learning Weather Models

DevFeed: [Distinguishing Initial-Condition and Model Error Using Machine-Learning Weather Models](<https://devfeed.tech/articles/distinguishing-initial-condition-and-model-error-using-machine-learning-weather-models-120529.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05592>)

Author: P. Trent Vonich, Gregory J. Hakim

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [lora](<https://devfeed.tech/topics/lora.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [error](<https://devfeed.tech/tags/error.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [physics-ao-ph](<https://devfeed.tech/tags/physics-ao-ph.md>), [weather](<https://devfeed.tech/tags/weather.md>)

### AI overview

The abstract finds that tuning GraphCast's initial conditions (ICs), its model weights with low-rank adaptation (LoRA), or both can similarly improve forecasts against a reanalysis-initialized control; the gains do not identify which source contributed the correction. To better separate them, the authors use Pangu-Weather to gate joint optimization: an IC update is retained only if it improves both models' forecasts, otherwise only the LoRA update is accepted. This constraint narrows the models' gap in mean forecast-error reduction from 64% to 10%, while GraphCast's combined IC and LoRA corrections retain improvements similar to ungated optimization. The authors suggest gating shifts model error that ungated optimization had encoded in ICs into LoRA corrections, potentially producing better analysis estimates.

### Source excerpt

arXiv:2611.05592v2 Announce Type: replace-cross Abstract: Differentiable weather models allow atmospheric initial conditions to be directly optimized to shadow a known trajectory, which we take from a reanalysis dataset. Here, we extend this optimization to include the forecast model, GraphCast, using low-rank adaptation (LoRA). We compare model optimization with initial-condition (IC) optimization, and then joint optimization, where both are tuned simultaneously. When compared against a control forecast initialized with reanalysis data, LoRA and IC optimization individually produce similar improvements. We find similar results when IC and LoRA are jointly optimized across a spectrum of solutions where a tuning coefficient smoothly shifts the weight of the joint optimization from all-LoRA to all-IC; forecast improvement is not unique to the relative contributions of model and IC corrections. To better discriminate the source of error, we introduce a second model, Pangu-Weather, as a supervisor that gates IC updates during joint optimization. This gated optimization is the same as before, except that IC updates at each epoch are accepted only when they improve the forecasts of both models; otherwise, only the LoRA update is accepted. Results show that this cross-model constraint substantially improves agreement between the two models in their response to the same optimized ICs, narrowing the gap in mean forecast error reduction from 64% to 10%. Moreover, when used together, the LoRA and IC corrections from the gated optimization yield GraphCast forecast improvements similar to those from the ungated optimization. These results imply that model error that is encoded in the ungated ICs is shifted to the LoRA corrections via gating, yielding IC corrections that may provide better analysis estimates.

## A Survey of Nonlinear Filtering Methods for Data Assimilation and Recent Advances in Generative AI-Enabled Score Filters

DevFeed: [A Survey of Nonlinear Filtering Methods for Data Assimilation and Recent Advances in Generative AI-Enabled Score Filters](<https://devfeed.tech/articles/a-survey-of-nonlinear-filtering-methods-for-data-assimilation-and-recent-advances-in-generative-ai-enabled-score-filters-120566.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07160>)

Author: Cath Pham, Kadesha Reynolds

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [applications](<https://devfeed.tech/tags/applications.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [curse-of-dimensionality](<https://devfeed.tech/tags/curse-of-dimensionality.md>), [data](<https://devfeed.tech/tags/data.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [dimension](<https://devfeed.tech/tags/dimension.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [estimator](<https://devfeed.tech/tags/estimator.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [filter](<https://devfeed.tech/tags/filter.md>), [foundations](<https://devfeed.tech/tags/foundations.md>), [free](<https://devfeed.tech/tags/free.md>), [function](<https://devfeed.tech/tags/function.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [math-pr](<https://devfeed.tech/tags/math-pr.md>), [score](<https://devfeed.tech/tags/score.md>), [survey](<https://devfeed.tech/tags/survey.md>)

### AI overview

Data assimilation estimates evolving system states by combining a dynamical model with partial, noisy observations, which requires filtering hidden-state distributions. The abstract contrasts three limitations: Kalman methods rely on Gaussian posteriors and can be biased with nonlinear observation operators; particle methods collapse in high dimensions; and kernel methods become too costly to maintain as dimension grows. The Ensemble Score Filter (EnSF) represents the filtering density through a score function approximated by a training-free Monte Carlo estimator, which the abstract presents as enabling stable filtering in high-dimensional chaotic systems. The survey examines 14 extensions: 12 retain this estimator, while two depart from it for planetary-scale deployment. These claims reflect the supplied abstract, not full-document coverage.

### Source excerpt

arXiv:2611.07160v1 Announce Type: new Abstract: Many real-world applications, such as numerical weather prediction or wildfire tracking, involve modeling highly nonlinear dynamical systems that are chaotic and influenced by various sources of uncertainty. To improve model prediction accuracy and reduce such uncertainties, data assimilation (DA) combines the dynamical model with partial, noisy observations to estimate the evolution of the system's state. Doing so depends on solving the optimal filtering problem: computing the conditional distribution of a hidden state given a sequence of observations. Classical approaches fail along three distinct axes: Kalman-based methods assume Gaussian posteriors and produce biased estimates under nonlinear observation operators; particle-based methods represent distributions with weighted samples and collapse in high dimensions due to the curse of dimensionality; and kernel-based methods move beyond discrete particle representations but cannot maintain their density approximation affordably as dimension grows. The Ensemble Score Filter (EnSF) avoids all three constraints by encoding the filtering density in a score function and approximating that score with a training-free Monte Carlo estimator, enabling stable filtering in high-dimensional, chaotic systems. This survey traces EnSF's mathematical foundations, establishes it as the state of the art for non-Gaussian, high-dimensional filtering, and examines fourteen extensions that expand its operational reach. Twelve of the fourteen extensions preserve this training-free Monte Carlo estimator at the core of the update, with only two departing from it to achieve planetary-scale deployment.

## Ai2 and Google collaborate on a new generation of climate models

DevFeed: [Ai2 and Google collaborate on a new generation of climate models](<https://devfeed.tech/articles/ai2-and-google-collaborate-on-a-new-generation-of-climate-models-118979.md>)

Original publisher: [Read original article](<https://allenai.org/blog/google-climate-partnership>)

Published: 2026-11-04T08:00:00Z

Content type: news

Language: en

Sources: [Ai2 Blog](<https://devfeed.tech/sources/ai2-blog.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [ace](<https://devfeed.tech/tags/ace.md>), [ai-modeling](<https://devfeed.tech/tags/ai-modeling.md>), [ai2](<https://devfeed.tech/tags/ai2.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [climate](<https://devfeed.tech/tags/climate.md>), [climate-modeling](<https://devfeed.tech/tags/climate-modeling.md>), [decades](<https://devfeed.tech/tags/decades.md>), [errors](<https://devfeed.tech/tags/errors.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [funding](<https://devfeed.tech/tags/funding.md>), [google](<https://devfeed.tech/tags/google.md>), [google-org](<https://devfeed.tech/tags/google-org.md>), [google-research](<https://devfeed.tech/tags/google-research.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [physics](<https://devfeed.tech/tags/physics.md>)

### AI overview

Ai2 plans to extend Google Research's NeuralGCM into NeuralGCM+, an open-source model for long-term climate projections. NeuralGCM combines physical equations for large-scale atmospheric dynamics with AI for local processes such as clouds and rainfall; Ai2 aims to couple it with ocean and sea-ice models to simulate decades and capture ocean heat redistribution. The work is supported by multimillion-dollar, three-year Google.org funding and Google Research technical support. Ai2 will test past regional temperature and rainfall errors against conventional models, improve projections for warmer conditions outside training, and release documented tools for researchers to adapt and extend, with better GPU performance. The approach may help address limits of conventional models' computational cost and of learned models' ability to generalize, but reliable future projections remain a central research challenge. The text distinguishes Google's nearer-term forecast focus from Ai2's years-to-decades climate focus.

### Source excerpt

With funding from Google.org and technical support from Google Research, Ai2 is developing NeuralGCM+, an open-source model designed to combine physics and AI to simulate the atmosphere and ocean together for faster, more reliable long-term climate projections.

## Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields

DevFeed: [Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields](<https://devfeed.tech/articles/wave-physics-as-representation-tensor-structured-neural-reconstruction-for-ocean-acoustic-fields-114588.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01680>)

Author: Yifan Sun, Panqi Chen, Weifeng Shi, Xiao Fu, Lei Cheng

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [angular](<https://devfeed.tech/tags/angular.md>), [bias](<https://devfeed.tech/tags/bias.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sd](<https://devfeed.tech/tags/cs-sd.md>), [eess-as](<https://devfeed.tech/tags/eess-as.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [field](<https://devfeed.tech/tags/field.md>), [inference](<https://devfeed.tech/tags/inference.md>), [learning](<https://devfeed.tech/tags/learning.md>), [neural](<https://devfeed.tech/tags/neural.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [physics](<https://devfeed.tech/tags/physics.md>), [rank](<https://devfeed.tech/tags/rank.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

TIDAL reconstructs 3D complex ocean acoustic fields from sparse measurements using a tensor structure derived from wave physics, without requiring the environment-dependent model parameters used by conventional physics-based recovery. The method derives a spatial-angular S/c representation from the Helmholtz equation and normal-mode propagation, then uses it as an inductive bias to decode measurements and aggregate information according to the sensing geometry. In a low-rank specialization, the representation is a rank-(L,L,1) block-term tensor decomposition linked to sufficient recovery conditions for structured sampling patterns. Across three sampling geometries, the abstract reports that TIDAL outperforms the baselines in reconstruction and inference speed, with the representation especially beneficial under limited data and model capacity. Evidence is limited to the supplied abstract.

### Source excerpt

arXiv:2611.01680v1 Announce Type: new Abstract: Reconstructing three-dimensional (3D) complex ocean acoustic fields from sparse measurements is challenging due to highly oscillatory wave structures and restricted sensing patterns/routes. Learning-based approaches fall into two categories. First, purely data-driven models can learn complex field patterns, but do not explicitly exploit wave physics that may enhance interpretability and reduce training costs. Second, physics-informed methods impose a specified physical equation as a reconstruction constraint, but often require environment-dependent parameters that are difficult to acquire. As a result, practical 3D acoustic field reconstruction that is both physically grounded and robust to uncertain environmental information remains largely unexplored. This work takes an alternative route: instead of solving a fully specified wave equation, it extracts a structured representation from wave physics and learns its components from data. From the Helmholtz equation and normal mode propagation, we derive a structured spatial-angular tensor representation, termed the S/c representation. Under a low-rank specialization, it takes the form of a rank-(L,L,1) block-term tensor decomposition, which connects structured sampling patterns/routes used in ocean sensing to sufficient conditions for field recovery. Building on this tensor representation, we propose TIDAL, a neural reconstructor that uses the S/c representation as an inductive bias for structured decoding and aligns information aggregation with the sampling geometry. The neural learner removes the need for known model parameters required by conventional physics-based recovery methods. Experiments across three structured sampling geometries show that TIDAL achieves the best reconstruction performance and fastest inference among baselines, with benefits from the physics-derived representation under limited data and model capacity.

## Climate downscaling with likelihood functional flow matching

DevFeed: [Climate downscaling with likelihood functional flow matching](<https://devfeed.tech/articles/climate-downscaling-with-likelihood-functional-flow-matching-103868.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33482>)

Author: Zhi-Song Liu, Helmi Toropainen, Ammar Kheder, Michael Boy

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [World models](<https://devfeed.tech/topics/world-models.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [climate](<https://devfeed.tech/tags/climate.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>)

### AI overview

CD-FFM represents high-resolution climate fields as continuous random fields that a single model can query at any location and resolution. Its pointwise velocity uses a noise prior fitted to the observed spectrum, and the method provides exact likelihoods for observations. In ERA5 downscaling to 1 km daily temperature over Fennoscandia, it reduced continuous ranked probability score by 27-31% versus regression and 12-18% versus a neural operator 40 times larger across three test years. It also outperformed a CorrDiff-style diffusion model while sampling about 50 times faster. The abstract reports transfer to precipitation and more affordable large kilometre-scale ensembles.

### Source excerpt

arXiv:2610.33482v2 Announce Type: replace Abstract: Decisions about heat, frost and flooding are made locally, yet reanalyses and climate models resolve tens of kilometres. Generative downscalers add kilometre-scale detail with uncertainty, but are tied to a grid, costly to sample and lack a tractable likelihood. Here we introduce CD-FFM, a functional flow-matching model that treats the high-resolution field as a continuous random field that one model can query at any location and resolution. Its velocity acts pointwise, so spatial variability comes from a noise prior fitted to the observed spectrum and every observation has an exact likelihood. Downscaling ERA5 to 1 km daily temperature over Fennoscandia, CD-FFM lowers the continuous ranked probability score by 27-31% against regression and 12-18% against a forty-times larger neural operator in each of three test years, and outperforms a CorrDiff-style diffusion model while sampling about fifty times faster. The same model transfers to precipitation and makes large kilometre-scale ensembles affordable.

## Pioneers Across Europe Deploy NVIDIA Earth-2 Open Models to Power Real-World Weather and Climate Prediction

DevFeed: [Pioneers Across Europe Deploy NVIDIA Earth-2 Open Models to Power Real-World Weather and Climate Prediction](<https://devfeed.tech/articles/pioneers-across-europe-deploy-nvidia-earth-2-open-models-to-power-real-world-weather-and-climate-prediction-95044.md>)

Original publisher: [Read original article](<https://blogs.nvidia.com/blog/europe-earth-2-open-models-weather-climate-prediction/>)

Author: Mike Pritchard

Published: 2026-10-22T05:00:19Z

Content type: release

Language: en

Sources: [NVIDIA](<https://devfeed.tech/sources/nvidia-blog.md>)

Topics: [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [geospatial](<https://devfeed.tech/topics/geospatial.md>), [DGX Spark](<https://devfeed.tech/topics/dgx-spark.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [ai](<https://devfeed.tech/tags/ai.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [climate](<https://devfeed.tech/tags/climate.md>), [daily](<https://devfeed.tech/tags/daily.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [developers](<https://devfeed.tech/tags/developers.md>), [earth-2](<https://devfeed.tech/tags/earth-2.md>), [energy](<https://devfeed.tech/tags/energy.md>), [europe](<https://devfeed.tech/tags/europe.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [gives](<https://devfeed.tech/tags/gives.md>), [global](<https://devfeed.tech/tags/global.md>), [gtc-2026](<https://devfeed.tech/tags/gtc-2026.md>), [models](<https://devfeed.tech/tags/models.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-earth-2](<https://devfeed.tech/tags/nvidia-earth-2.md>), [open](<https://devfeed.tech/tags/open.md>), [power](<https://devfeed.tech/tags/power.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [weather](<https://devfeed.tech/tags/weather.md>)

### AI overview

NVIDIA Earth-2 combines open models and tools that organizations can adapt with local observations and expertise for regional weather and environmental work. StormScope EU uses EUMETSAT observations across 16 Meteosat channels to predict cloud conditions over Europe at 10-minute intervals; a GTC Berlin demo runs forecasts with Earth2Studio and serves updated map tiles through Earthmover. Workflows can pair StormScope with CorrDiff for local detail, while PhysicsNeMo supports training and customization. The excerpt describes distinct applications: AXA uses FourCastNet 3 to study cyclone risk across more than 1,000 simulated seasons; Vaisala Xweather is adapting StormScope with lightning data; Manchester researchers adapted CorrDiff for U.K. air-quality modeling; TotalEnergies is evaluating solar-radiation nowcasts at two photovoltaic sites; and Space42 developed a CorrDiff- and PhysicsNeMo-based method that estimates surface heights from radar imagery and includes uncertainty maps.

### Source excerpt

Weather forecasts shape more than daily plans; timely weather information is crucial for energy producers, insurers and transport operators to plan around changing conditions. A global forecast can show a storm taking shape, but decisions about solar farms, shipping routes or insured property depend on what happens locally. NVIDIA Earth-2 gives developers and researchers a [...]

[Next page](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md?cursor=WyIyMDI2LTEwLTIyVDA1OjAwOjE5KzAwOjAwIiwgImEwZGUzMDZjLWU4MGEtNGU1OC1hN2RjLWQ2ZjhlOGY3Y2IwMCJd>)