ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
Sungduk Yu, Walter Hannah, Liran Peng, Jerry Lin, Mohamed Aziz Bhouri, Ritwik Gupta, Björn Lütjens, Justus Christopher Will
Abstract
Modern climate projections lack adequate spatial and temporal resolution due to computational constraints. A consequence is inaccurate and imprecise predictions of critical processes such as storms. Hybrid methods that combine physics with machine learning (ML) have introduced a new generation of higher fidelity climate simulators that can sidestep Moore's Law by outsourcing compute-hungry, short, high-resolution simulations to ML emulators. However, this hybrid ML-physics simulation approach requires domain-specific treatment and has been inaccessible to ML experts because of lack of training data and relevant, easy-to-use workflows. We present ClimSim, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, developed by a consortium of climate scientists and ML researchers. It consists of 5.7 billion pairs of multivariate input and output vectors that isolate the influence of locally-nested, high-resolution, high-fidelity physics on a host climate simulator's macro-scale physical state. The dataset is global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators. We implement a range of deterministic and stochastic regression baselines to highlight the ML challenges and their scoring. The data (https://huggingface.co/datasets/LEAP/ClimSim_high-res) and code (https://leap-stc.github.io/ClimSim) are released openly to support the development of hybrid ML-physics and high-fidelity climate simulations for the benefit of science and society.
BibTeX
@inproceedings{
yu2023climsim,
title={ClimSim: A large multi-scale dataset for hybrid physics-{ML} climate emulation},
author={Sungduk Yu and Walter Hannah and Liran Peng and Jerry Lin and Mohamed Aziz Bhouri and Ritwik Gupta and Bj{\"o}rn L{\"u}tjens and Justus Christopher Will and Gunnar Behrens and Julius Busecke and Nora Loose and Charles I Stern and Tom Beucler and Bryce Harrop and Benjamin R Hillman and Andrea Jenney and Savannah Ferretti and Nana Liu and Anima Anandkumar and Noah D Brenowitz and Veronika Eyring and Nicholas Geneva and Pierre Gentine and Stephan Mandt and Jaideep Pathak and Akshay Subramaniam and Carl Vondrick and Rose Yu and Laure Zanna and Tian Zheng and Ryan Abernathey and Fiaz Ahmed and David C Bader and Pierre Baldi and Elizabeth Barnes and Christopher Bretherton and Peter Caldwell and Wayne Chuang and Yilun Han and YU HUANG and Fernando Iglesias-Suarez and Sanket Jantre and Karthik Kashinath and Marat Khairoutdinov and Thorsten Kurth and Nicholas Lutsko and Po-Lun Ma and Griffin Mooers and J. David Neelin and David Randall and Sara Shamekh and Mark A Taylor and Nathan Urban and Janni Yuval and Guang Zhang and Michael Pritchard},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2023},
url={https://openreview.net/forum?id=W5If9P1xqO}
}