SurroFlow: A Flow-Based Surrogate Model for Parameter Space Exploration and Uncertainty Quantification

TL;DR

SurroFlow is a novel flow-based surrogate model that enables accurate simulation predictions, uncertainty quantification, and efficient parameter exploration, significantly reducing computational costs in scientific simulations.

Contribution

We introduce SurroFlow, a normalizing flow-based surrogate model that supports invertible mappings, uncertainty quantification, and efficient parameter space exploration.

Findings

Accurately predicts simulation outputs for given parameters.

Supports uncertainty quantification in data generation.

Reduces computational costs in simulation exploration.

Abstract

Existing deep learning-based surrogate models facilitate efficient data generation, but fall short in uncertainty quantification, efficient parameter space exploration, and reverse prediction. In our work, we introduce SurroFlow, a novel normalizing flow-based surrogate model, to learn the invertible transformation between simulation parameters and simulation outputs. The model not only allows accurate predictions of simulation outcomes for a given simulation parameter but also supports uncertainty quantification in the data generation process. Additionally, it enables efficient simulation parameter recommendation and exploration. We integrate SurroFlow and a genetic algorithm as the backend of a visual interface to support effective user-guided ensemble simulation exploration and visualization. Our framework significantly reduces the computational costs while enhancing the reliability and exploration capabilities of scientific surrogate models.