# Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework

DevFeed: [Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework](<https://devfeed.tech/articles/microdroplet-generator-surrogate-enhancement-and-inverse-design-through-an-uncertainty-guided-framework-118471.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06464>)

Author: David Gabriel Harispe, Mat\\'ias Gerard, Pablo A. Kler

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

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

Topics: [Simulation and Design](<https://devfeed.tech/topics/simulation-and-design.md>), [Complex Systems](<https://devfeed.tech/topics/complex-systems.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [applications](<https://devfeed.tech/tags/applications.md>), [balancing](<https://devfeed.tech/tags/balancing.md>), [cases](<https://devfeed.tech/tags/cases.md>), [class](<https://devfeed.tech/tags/class.md>), [classification](<https://devfeed.tech/tags/classification.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [consensus](<https://devfeed.tech/tags/consensus.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [design](<https://devfeed.tech/tags/design.md>), [device](<https://devfeed.tech/tags/device.md>), [diameter](<https://devfeed.tech/tags/diameter.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generator](<https://devfeed.tech/tags/generator.md>), [inverse-design](<https://devfeed.tech/tags/inverse-design.md>), [physics-flu-dyn](<https://devfeed.tech/tags/physics-flu-dyn.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

## AI overview

The framework combines Volume-of-Fluid simulations with neural network ensembles to predict droplet flow regimes and diameters, then uses ensemble uncertainty to guide additional simulations. Uncertainty is concentrated near regime transition boundaries; targeted enrichment also addresses class imbalance before retraining the ensembles. For inverse design, Particle Swarm Optimization searches constrained configurations while accounting for prediction accuracy, confidence, and physical consistency. On independent test datasets, enrichment nearly doubled the share of diameter predictions within 0-3% error and substantially reduced cases above 10% error. The reported procedure found physically realizable configurations meeting target droplet sizes, while reducing computational costs.

## Source excerpt

arXiv:2611.06464v1 Announce Type: cross Abstract: Microfluidic droplet generation is critical for many applications, yet efficient device design in high-dimensional parameter spaces remains computationally prohibitive due to complex multiphase flow dynamics. This work presents a unified methodology that couples adaptive surrogate enhancement with simulation-driven inverse design. High-fidelity Volume-of-Fluid simulations provide ground-truth data, while neural network ensembles predict flow regimes and droplet diameters. Ensemble-based uncertainty quantification identifies epistemic uncertainty using consensus levels for regime classification and the coefficient of variation for diameter prediction, revealing that uncertainty concentrates near regime transition boundaries where physics is highly sensitive to parameter perturbations. A physics-informed enrichment strategy targets these critical zones and addresses class imbalances by deploying additional targeted simulations and retraining the surrogates forming the ensembles. A framework that integrates Particle Swarm Optimization for constrained inverse design, balancing accuracy with predictive confidence and physical consistency is therefore proposed. Validation on independent test datasets demonstrates that the enriched ensembles achieve higher accuracy, with the fraction of predictions within the 0-3% error range on droplet diameter nearly doubling, and high-error cases (above 10%) dropping substantially. The inverse design procedure reliably identifies physically realizable configurations meeting target droplet sizes. This approach significantly reduces computational costs while ensuring reliable predictions, offering a framework with potential applicability to the optimization of a broad range of microfluidic systems.