# PhysXAI: A Theoretical Framework for Diagnosing Physical Hallucinations in Weather Foundation Models

DevFeed: [PhysXAI: A Theoretical Framework for Diagnosing Physical Hallucinations in Weather Foundation Models](<https://devfeed.tech/articles/physxai-a-theoretical-framework-for-diagnosing-physical-hallucinations-in-weather-foundation-models-132951.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15053>)

Author: Anjan Mahapatra, Nikhil Raj

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

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>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [framework](<https://devfeed.tech/tags/framework.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [models](<https://devfeed.tech/tags/models.md>), [physics](<https://devfeed.tech/tags/physics.md>), [python](<https://devfeed.tech/tags/python.md>), [theoretical](<https://devfeed.tech/tags/theoretical.md>), [weather](<https://devfeed.tech/tags/weather.md>)

## AI overview

PhysXAI is a learnable framework for detecting and attributing physical inconsistencies in weather forecasts while separating physical plausibility from forecast error. It encodes conservation, dynamical, spectral, cross-variable, and spatiotemporal residuals, using a contrastive objective intended to keep diagnostic representations grounded in physical deviations and adaptive gradient weighting to balance objectives. Its outputs include spatial hallucination maps, violation types, and calibrated Bayesian uncertainty. The abstract reports comparisons across ERA5, WeatherBench 2, and MERRA-2 using forecasts from GraphCast, Pangu-Weather, and NeuralGCM; it provides no quantitative results or specific performance comparisons.

## Source excerpt

arXiv:2611.15053v1 Announce Type: new Abstract: Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling. We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies. Unlike existing post-hoc metric suites, PhysXAI is a learnable system that explicitly decouples forecast error from physical plausibility. We formalise the problem through a novel joint condition on numerical and physical residuals, and introduce a multi-branch encoder that extracts representations from conservation, dynamical, spectral, cross-variable, and spatiotemporal residuals. A key innovation is a physics-consistency contrastive learning objective, which we theoretically show the latent representation to be approximately isometric to the physical residual space, ensuring that diagnostic decisions remain grounded in physically meaningful deviations. We further derive an adaptive multi-objective loss with gradient-based weighting to balance competing diagnostic objectives. The framework produces spatially resolved hallucination maps, violation-type classifications, and calibrated Bayesian uncertainty, enabling both detection and interpretable attribution of physical inconsistencies. We conduct a comprehensive comparative evaluation of PhysXAI across ERA5, WeatherBench 2, and MERRA-2, using forecasts from GraphCast, Pangu-Weather, and NeuralGCM, with Python-written code and a fully reproducible experimental protocol. Our theoretical analysis and empirical evaluation establish PhysXAI as a principled framework for diagnosing physical hallucinations and advancing trustworthy AI for weather forecasting.