The Well: A Large-Scale Collection of Diverse Physics Simulations for Machine Learning
Abstract
Machine learning 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 the Well: a large-scale collection of datasets containing numerical simulations of a wide variety of spatiotemporal physical systems. The Well draws from domain experts 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 posed by the complex dynamics of the Well. The code and data is available at https://github.com/PolymathicAI/the_well.
Cite
Text
Ohana et al. "The Well: A Large-Scale Collection of Diverse Physics Simulations for Machine Learning." Neural Information Processing Systems, 2024. doi:10.52202/079017-1430Markdown
[Ohana et al. "The Well: A Large-Scale Collection of Diverse Physics Simulations for Machine Learning." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/ohana2024neurips-well/) doi:10.52202/079017-1430BibTeX
@inproceedings{ohana2024neurips-well,
title = {{The Well: A Large-Scale Collection of Diverse Physics Simulations for Machine Learning}},
author = {Ohana, Ruben and McCabe, Michael and Meyer, Lucas and Morel, Rudy and Agocs, Fruzsina J. and Beneitez, Miguel and Berger, Marsha and Burkhart, Blakesley and Dalziel, Stuart B. and Fielding, Drummond B. and Fortunato, Daniel and Goldberg, Jared A. and Hirashima, Keiya and Jiang, Yan-Fei and Kerswell, Rich R. and Maddu, Suryanarayana and Miller, Jonah and Mukhopadhyay, Payel and Nixon, Stefan S. and Shen, Jeff and Watteaux, Romain and Blancard, Bruno Régaldo-Saint and Rozet, François and Parker, Liam H. and Cranmer, Miles and Ho, Shirley},
booktitle = {Neural Information Processing Systems},
year = {2024},
doi = {10.52202/079017-1430},
url = {https://mlanthology.org/neurips/2024/ohana2024neurips-well/}
}