Machine Learning Visualization Tool for Exploring Parameterized Hydrodynamics
This tool addresses the problem of data exploration for computational scientists in hydrodynamics, but it is incremental as it applies existing machine learning methods to a new domain-specific dataset.
The paper tackles the challenge of exploring large-scale parameterized hydrodynamics simulation datasets by developing an interactive machine learning tool that compresses, browses, and interpolates terabytes of data, enabling computational scientists to visualize scenarios, conduct sensitivity analyses, and optimize experiments.
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.