SurroFlow: A Flow-Based Surrogate Model for Parameter Space Exploration and Uncertainty Quantification
This work addresses the need for more reliable and explorable surrogate models in scientific simulations, though it appears incremental as it builds on existing flow-based methods.
The authors tackled the problem of deep learning-based surrogate models lacking uncertainty quantification and efficient parameter space exploration by introducing SurroFlow, a normalizing flow-based model that learns invertible transformations between simulation parameters and outputs, resulting in significantly reduced computational costs and enhanced reliability and exploration capabilities.
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.