elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation

Yu, Sungduk and Hannah, Walter and Peng, Liran and Lin, Jerry and Bhouri, Mohamed Aziz and Gupta, Ritwik and Lütjens, Björn and Will, Justus Christopher and Behrens, Gunnar and Busecke, Julius and Loose, Nora and Stern, Charles I. and Beucler, Tom and Harrop, Bryce E. and Hillman, Benjamin R. and Jenney, Andrea M. and Ferretti, Savannah L. and Liu, Nana and Anandkumar, Anima and Brenowitz, Noah D. and Eyring, Veronika and Geneva, Nicholas and Gentine, Pierre and Mandt, Stephan and Pathak, Jaideep and Subramaniam, Akshay and Vondrick, Carl and Yu, Rose and Zanna, Laure and Zheng, Tian and Abernathey, Ryan P. and Ahmed, Fiaz and Bader, David C. and Baldi, Pierre and Barnes, Elizabeth and Bretherton, Christopher and Caldwell, Peter and Chuang, Wayne and Han, Yilun and Huang, Yu and Iglesias-Suarez, Fernando and Jantre, Sanket and Kashinath, Karthik and Khairoutdinov, Marat and Kurth, Thorsten and Lutsko, Nicholas and Ma, Po-Lun and Mooers, Griffin and Neelin, J. D. and Randall, David and Shamekh, Sara and Taylor, Mark A. and Urban, Nathan M. and Yuval, Janni and Zhang, Guang and Pritchard, Michael (2023) ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation. In: 37th Conference on Neural Information Processing Systems, NeurIPS 2023. 37th Conference on Neural Information Processing Systems, 2023-12-10 - 2023-12-16, 900 Convention Center Boulevard, New Orleans, Louisiana, 70130, United States. doi: 10.48550/arXiv.2306.08754.

[img] PDF
14MB

Official URL: https://nips.cc/virtual/2023/poster/73569

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.

Item URL in elib:https://elib.dlr.de/199426/
Document Type:Conference or Workshop Item (Poster)
Title:ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Yu, SungdukUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Hannah, WalterLawrence Livermore National LabUNSPECIFIEDUNSPECIFIED
Peng, LiranUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Lin, JerryUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Bhouri, Mohamed AzizColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Gupta, RitwikUniversity of California, BerkeleyUNSPECIFIEDUNSPECIFIED
Lütjens, BjörnMassachusetts Institute of TechnologyUNSPECIFIEDUNSPECIFIED
Will, Justus ChristopherUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Behrens, GunnarDLR, IPAhttps://orcid.org/0000-0002-5921-5327UNSPECIFIED
Busecke, JuliusColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Loose, NoraPrinceton UniversityUNSPECIFIEDUNSPECIFIED
Stern, Charles I.Columbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Beucler, TomUniversity of Lausanne, Lausanne, Switzerlandhttps://orcid.org/0000-0002-5731-1040UNSPECIFIED
Harrop, Bryce E.Pacific Northwest National Laboratory, Richland, WA, USAUNSPECIFIEDUNSPECIFIED
Hillman, Benjamin R.Sandia National Laboratories, Albuquerque, USAUNSPECIFIEDUNSPECIFIED
Jenney, Andrea M.University of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Ferretti, Savannah L.University of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Liu, NanaUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Anandkumar, AnimaNVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Brenowitz, Noah D.NVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Eyring, VeronikaDLR, IPAhttps://orcid.org/0000-0002-6887-4885UNSPECIFIED
Geneva, NicholasNVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Gentine, PierreColumbia University, New York, USAhttps://orcid.org/0000-0002-0845-8345UNSPECIFIED
Mandt, StephanUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Pathak, JaideepNVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Subramaniam, AkshayNVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Vondrick, CarlColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Yu, RoseUC San DiegoUNSPECIFIEDUNSPECIFIED
Zanna, LaureNew York UniversityUNSPECIFIEDUNSPECIFIED
Zheng, TianColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Abernathey, Ryan P.Columbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Ahmed, FiazUC Los AngelesUNSPECIFIEDUNSPECIFIED
Bader, David C.Lawrence Livermore National LabUNSPECIFIEDUNSPECIFIED
Baldi, PierreUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Barnes, ElizabethColorado State UniversityUNSPECIFIEDUNSPECIFIED
Bretherton, ChristopherAllen AIUNSPECIFIEDUNSPECIFIED
Caldwell, PeterLawrence Livermore National Laboratory, California USAUNSPECIFIEDUNSPECIFIED
Chuang, WayneColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Han, YilunTsinghua University, Beijing, ChinaUNSPECIFIEDUNSPECIFIED
Huang, YuColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Iglesias-Suarez, FernandoDLR, IPAhttps://orcid.org/0000-0003-3403-8245UNSPECIFIED
Jantre, SanketBrookhaven National LaboratoryUNSPECIFIEDUNSPECIFIED
Kashinath, KarthikNVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Khairoutdinov, MaratStony Brook UniversityUNSPECIFIEDUNSPECIFIED
Kurth, ThorstenNVIDIA Corporation, Santa Clara, USAUNSPECIFIEDUNSPECIFIED
Lutsko, NicholasUC San DiegoUNSPECIFIEDUNSPECIFIED
Ma, Po-LunPacific Northwest National Laboratory, Richland, WA, Washington, USAhttps://orcid.org/0000-0003-3109-5316UNSPECIFIED
Mooers, GriffinUniversity of California, Irvine, USAUNSPECIFIEDUNSPECIFIED
Neelin, J. D.UC Los AngelesUNSPECIFIEDUNSPECIFIED
Randall, DavidColorado State UniversityUNSPECIFIEDUNSPECIFIED
Shamekh, SaraColumbia University, New York, USAUNSPECIFIEDUNSPECIFIED
Taylor, Mark A.Sandia National Laboratories, Albuquerque, USAUNSPECIFIEDUNSPECIFIED
Urban, Nathan M.Brookhaven National LaboratoryUNSPECIFIEDUNSPECIFIED
Yuval, JanniMassachusetts Institute of TechnologyUNSPECIFIEDUNSPECIFIED
Zhang, GuangUC San DiegoUNSPECIFIEDUNSPECIFIED
Pritchard, MichaelUniversity of California Irvine, Irvine, CA, USAhttps://orcid.org/0000-0002-0340-6327UNSPECIFIED
Date:2023
Journal or Publication Title:37th Conference on Neural Information Processing Systems, NeurIPS 2023
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI:10.48550/arXiv.2306.08754
Status:Published
Keywords:machine learning; benchmark; dataset
Event Title:37th Conference on Neural Information Processing Systems
Event Location:900 Convention Center Boulevard, New Orleans, Louisiana, 70130, United States
Event Type:international Conference
Event Start Date:10 December 2023
Event End Date:16 December 2023
Organizer:Neural Information Processing Systems
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Atmospheric and climate research
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Atmospheric Physics > Earth System Model Evaluation and Analysis
Deposited By: Iglesias-Suarez, Dr. Fernando
Deposited On:21 Nov 2023 11:09
Last Modified:24 Apr 2024 21:00

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.