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

2024-11-30

Neural Information Processing Systems

AI Summary

Existing physical simulation benchmarks suffer from limited scale and narrow domain coverage, hindering comprehensive evaluation of machine learning models on complex dynamical systems. To address this, we introduce the first 15-TB, multi-domain, high-fidelity physics simulation dataset—encompassing 16 spatiotemporal physical systems, including biological dynamics, fluid mechanics, acoustics, and cosmic magnetohydrodynamics. It is the first benchmark to systematically integrate cross-scale and interdisciplinary numerical simulation data. The dataset adopts standardized HDF5 storage and a unified PyTorch interface, enabling efficient distributed loading and spatiotemporal modeling. We fully open-source all code, data, and an extensible benchmarking framework. Empirical evaluation reveals significant performance bottlenecks of current ML surrogate models under strongly nonlinear, multiscale-coupled regimes. This dataset fills a critical gap in general-purpose evaluation infrastructure for complex physical systems and establishes foundational resources for physics-informed AI research.

Technology Category

• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

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.

Problem

• Provides diverse physics simulations for machine learning.
• Addresses lack of large-scale datasets for evaluation.
• Offers unified interface for training and evaluation.

Innovation

• Large-scale diverse physics simulations
• Unified PyTorch interface provided
• Example baselines introduced