An Extensible Benchmark Suite for Learning to Simulate Physical Systems
arXiv:2108.07799
Abstract
Simulating physical systems is a core component of scientific computing, encompassing a wide range of physical domains and applications. Recently, there has been a surge in data-driven methods to complement traditional numerical simulations methods, motivated by the opportunity to reduce computational costs and/or learn new physical models leveraging access to large collections of data. However, the diversity of problem settings and applications has led to a plethora of approaches, each one evaluated on a different setup and with different evaluation metrics. We introduce a set of benchmark problems to take a step towards unified benchmarks and evaluation protocols. We propose four representative physical systems, as well as a collection of both widely used classical time integrators and representative data-driven methods (kernel-based, MLP, CNN, nearest neighbors). Our framework allows evaluating objectively and systematically the stability, accuracy, and computational efficiency of data-driven methods. Additionally, it is configurable to permit adjustments for accommodating other learning tasks and for establishing a foundation for future developments in machine learning for scientific computing.
arXiv commentAccepted to NeurIPS 2021 track on datasets and benchmarks
References in corpus (12)
- Scikit-learn: Machine Learning in Python
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
- Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems
- Hamiltonian Graph Networks with ODE Integrators
- Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
- DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks
- Image-based reconstruction for the impact problems by using DPNNs
- Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method