Poster
in
Workshop: D3S3: Data-driven and Differentiable Simulations, Surrogates, and Solvers

The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

Ruben Ohana ⋅ Michael McCabe ⋅ Lucas Meyer ⋅ Rudy Morel ⋅ Fruzsina Agocs ⋅ Miguel Beneitez ⋅ Marsha Berger ⋅ Blakesly Burkhart ⋅ Stuart Dalziel ⋅ Drummond Fielding ⋅ Daniel Fortunato ⋅ Jared Goldberg ⋅ Keiya Hirashima ⋅ Yan-Fei Jiang ⋅ Rich Kerswell ⋅ Suryanarayana Maddu ⋅ Jonah Miller ⋅ Payel Mukhopadhyay ⋅ Stefan Nixon ⋅ Jeff Shen ⋅ Romain Watteaux ⋅ Bruno Régaldo-Saint Blancard ⋅ Liam Parker ⋅ Miles Cranmer ⋅ Shirley Ho

Keywords: operator learning numerical simulations fluid-dynamics partial differential equations

Project Page [ OpenReview]

Abstract

Machine learning (ML) based surrogate models offer researchers powerful tools for accelerating simulation-based workflows. However, as standard datasets in this space often cover small classes of physical behavior, it can be difficult to evaluate the efficacy of new approaches. To address this gap, we introduce \emph{the Well:} a large-scale collection of datasets containing numerical simulations of a wide variety of spatiotemporal physical systems. The Well draws from domain scientists and numerical software developers to provide 15TB of data across 16 datasets covering diverse domains such as biological systems, fluid dynamics, acoustic scattering, as well as magneto-hydrodynamic simulations of extra-galactic fluids or supernova explosions. These datasets can be used individually or as part of a broader benchmark suite. To facilitate usage of the Well, we provide a unified PyTorch interface for training and evaluating models. We demonstrate the function of this library by introducing example baselines that highlight the new challenges poses by the complex dynamics of the Well.

Chat is not available.