Microdroplet generator design improved using uncertainty aware simulations
Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework
Artificial Intelligence
Summary
Designing devices that make tiny droplets in fluids is complicated and takes a lot of computer work because the flows are tricky to predict. The authors created a smart process that uses neural networks to estimate droplet sizes and flow types, plus special checks for when the predictions might be wrong. They then focus more computer effort on the tricky spots where the predictions are uncertain or less accurate, improving the models. Their method cuts down on computing time while making better and more reliable droplet size predictions for different designs.
What this means in practice
- •For microfluidic device engineers: Create droplet generators that meet target sizes faster and with fewer simulations by using uncertainty-guided model improvements.
- •For chemical processing teams: Optimize microfluidic systems for producing droplets with specific properties more efficiently by integrating data-driven surrogate models.
Authors
David Gabriel Harispe, Matías Gerard, Pablo A. Kler
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.