PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
Preprint
Abstract
Machine learning-based modeling of physical systems has experienced increased interest in recent years. Despite some impressive progress, there is still a lack of benchmarks for Scientific ML that are easy to use but still challenging and representative of a wide range of problems. We introduce PDEBench, a benchmark suite of time-dependent simulation tasks based on Partial Differential Equations (PDEs). PDEBench comprises both code and data to benchmark the performance of novel machine learning models against both classical numerical simulations and machine learning baselines. Our proposed set of benchmark problems contribute the following unique features: (1) A much wider range of PDEs compared to existing benchmarks, ranging from relatively common examples to more realistic and difficult problems; (2) much larger ready-to-use datasets compared to prior work, comprising multiple simulation runs across a larger number of initial and boundary conditions and PDE parameters; (3) more extensible source codes with user-friendly APIs for data generation and baseline results with popular machine learning models (FNO, U-Net, PINN, Gradient-Based Inverse Method). PDEBench allows researchers to extend the benchmark freely for their own purposes using a standardized API and to compare the performance of new models to existing baseline methods. We also propose new evaluation metrics with the aim to provide a more holistic understanding of learning methods in the context of Scientific ML. With those metrics we identify tasks which are challenging for recent ML methods and propose these tasks as future challenges for the community. The code is available at https://github.com/pdebench/PDEBench.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- NVIDIA SimNet™: An AI-Accelerated Multi-Physics Simulation Framework2021
- Deep Neural Networks Motivated by Partial Differential EquationsJournal of Mathematical Imaging and Vision, 2019
- Emulation Engines: Choice and Quantification of Uncertainty for Complex Hydrological ModelsJournal of Agricultural, Biological and Environmental Statistics, 2017
- The Finite Volume Method in Computational Fluid Dynamics2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Sorption isotherms: A review on physical bases, modeling and measurementApplied Geochemistry, 2007
- Restoration of the contact surface in the HLL-Riemann solverShock Waves, 1994
- Towards the ultimate conservative difference scheme. V. A second-order sequel to Godunov's methodJournal of Computational Physics, 1979
- On Bayesian Methods for Seeking the Extremum1975
- ber die partiellen Differenzengleichungen der mathematischen PhysikMathematische Annalen, 1928