Work

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

Year: 2024

Type: article

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.

Source: IEEE Transactions on Visualization and Computer Graphics

DOI: 10.1109/tvcg.2024.3456372

Authors: Jingyi Shen, Yuhan Duan, Han-Wei Shen

Institution: The Ohio State University

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, U.S. Department of Energy, Division of Information and Intelligent Systems, Los Alamos National Laboratory

Awards: III: Medium: Collaborative Research: Deep Learning for In Situ Analysis and Visualization, ACTIONABLE INTELLIGENT VISUAL ANALYTICS OF ENSEMBLES, G4305017934