Machine Learning Visualization Tool for Exploring Parameterized Hydrodynamics

TL;DR

This paper introduces an interactive machine learning visualization tool designed to efficiently explore and analyze large, parameterized hydrodynamic simulation datasets, enabling rapid sensitivity analysis and optimization.

Contribution

The paper presents a novel ML-based visualization tool that compresses, browses, and interpolates large hydrodynamic simulation data for enhanced scientific exploration.

Findings

Enables quick visualization of complex hydrodynamic scenarios

Facilitates sensitivity analysis and parameter optimization

Handles datasets of terabyte scale efficiently

Abstract

We are interested in the computational study of shock hydrodynamics, i.e. problems involving compressible solids, liquids, and gases that undergo large deformation. These problems are dynamic and nonlinear and can exhibit complex instabilities. Due to advances in high performance computing it is possible to parameterize a hydrodynamic problem and perform a computational study yielding $\mathcal{O}\left({\rm TB}\right)$ of simulation state data. We present an interactive machine learning tool that can be used to compress, browse, and interpolate these large simulation datasets. This tool allows computational scientists and researchers to quickly visualize "what-if" situations, perform sensitivity analyses, and optimize complex hydrodynamic experiments.