Machine learning feature analysis illuminates disparity between E3SM climate models and observed climate change

Nichol, J. Jake; Peterson, Matthew G.; Peterson, Kara J.; Fricke, G. Matthew; Moses, Melanie E.

doi:10.1016/j.cam.2021.113451

Machine learning feature analysis illuminates disparity between E3SM climate models and observed climate change

Journal Article · Mon Mar 29 00:00:00 EDT 2021 · Journal of Computational and Applied Mathematics

DOI:https://doi.org/10.1016/j.cam.2021.113451· OSTI ID:1782577

^[1]; Peterson, Matthew G. ^[2]; Peterson, Kara J. ^[2]; ^[3]; Moses, Melanie E. ^[4]

Univ. of New Mexico, Albuquerque, NM (United States); Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Univ. of New Mexico, Albuquerque, NM (United States)
Univ. of New Mexico, Albuquerque, NM (United States); Santa Fe Inst., NM (United States)

In September of 2020, Arctic sea ice extent was the second-lowest on record. State of the art climate prediction uses Earth system models (ESMs), driven by systems of differential equations representing the laws of physics. Previously, these models have tended to underestimate Arctic sea ice loss. The issue is grave because accurate modeling is critical for economic, ecological, and geopolitical planning. We use machine learning techniques, including random forest regression and Gini importance, to show that the Energy Exascale Earth System Model (E3SM) relies too heavily on just one of the ten chosen climatological quantities to predict September sea ice averages. Furthermore, E3SM gives too much importance to six of those quantities when compared to observed data. Finally, identifying the features that climate models incorrectly rely on should allow climatologists to improve prediction accuracy.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC04-94AL85000; NA0003525

OSTI ID:: 1782577

Report Number(s):: SAND--2021-1306J; 693876

Journal Information:: Journal of Computational and Applied Mathematics, Journal Name: Journal of Computational and Applied Mathematics Vol. 395; ISSN 0377-0427

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (16)

Bagging predictors Breiman, Leo Machine Learning, Vol. 24, Issue 2, p. 123-140 https://doi.org/10.1007/BF00058655	journal	August 1996
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Arctic sea ice decline: Faster than forecast: ARCTIC ICE LOSS-FASTER THAN FORECAST Stroeve, Julienne; Holland, Marika M.; Meier, Walt Geophysical Research Letters, Vol. 34, Issue 9 https://doi.org/10.1029/2007GL029703	journal	May 2007
Trends in Arctic sea ice extent from CMIP5, CMIP3 and observations: ARCTIC SEA ICE EXTENT FROM CMIP5 Stroeve, Julienne C.; Kattsov, Vladimir; Barrett, Andrew Geophysical Research Letters, Vol. 39, Issue 16 https://doi.org/10.1029/2012GL052676	journal	August 2012
Arctic sea-ice decline weakens the Atlantic Meridional Overturning Circulation Sévellec, Florian; Fedorov, Alexey V.; Liu, Wei Nature Climate Change, Vol. 7, Issue 8 https://doi.org/10.1038/nclimate3353	journal	July 2017
New Trans-Arctic shipping routes navigable by midcentury Smith, L. C.; Stephenson, S. R. Proceedings of the National Academy of Sciences, Vol. 110, Issue 13 https://doi.org/10.1073/pnas.1214212110	journal	March 2013
The NumPy Array: A Structure for Efficient Numerical Computation van der Walt, Stéfan; Colbert, S. Chris; Varoquaux, Gaël Computing in Science & Engineering, Vol. 13, Issue 2 https://doi.org/10.1109/MCSE.2011.37	journal	March 2011
Persistence and Inherent Predictability of Arctic Sea Ice in a GCM Ensemble and Observations Blanchard-Wrigglesworth, Edward; Armour, Kyle C.; Bitz, Cecilia M. Journal of Climate, Vol. 24, Issue 1 https://doi.org/10.1175/2010JCLI3775.1	journal	January 2011
An Overview of CMIP5 and the Experiment Design Taylor, Karl E.; Stouffer, Ronald J.; Meehl, Gerald A. Bulletin of the American Meteorological Society, Vol. 93, Issue 4 https://doi.org/10.1175/BAMS-D-11-00094.1	journal	April 2012
The Community Earth System Model (CESM) Large Ensemble Project: A Community Resource for Studying Climate Change in the Presence of Internal Climate Variability Kay, J. E.; Deser, C.; Phillips, A. Bulletin of the American Meteorological Society, Vol. 96, Issue 8 https://doi.org/10.1175/BAMS-D-13-00255.1	journal	August 2015
Evaluation and Intercomparison of Cloud Fraction and Radiative Fluxes in Recent Reanalyses over the Arctic Using BSRN Surface Observations Zib, Behnjamin J.; Dong, Xiquan; Xi, Baike Journal of Climate, Vol. 25, Issue 7 https://doi.org/10.1175/JCLI-D-11-00147.1	journal	April 2012
Sea Ice Trends in Climate Models Only Accurate in Runs with Biased Global Warming Rosenblum, Erica; Eisenman, Ian Journal of Climate, Vol. 30, Issue 16 https://doi.org/10.1175/JCLI-D-16-0455.1	journal	August 2017
Processes Controlling Arctic and Antarctic Sea Ice Predictability in the Community Earth System Model Ordoñez, Ana C.; Bitz, Cecilia M.; Blanchard-Wrigglesworth, Edward Journal of Climate, Vol. 31, Issue 23 https://doi.org/10.1175/JCLI-D-18-0348.1	journal	December 2018
Arcing classifier (with discussion and a rejoinder by the author) Breiman, Leo The Annals of Statistics, Vol. 26, Issue 3 https://doi.org/10.1214/aos/1024691079	journal	June 1998
Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization Eyring, Veronika; Bony, Sandrine; Meehl, Gerald A. Geoscientific Model Development, Vol. 9, Issue 5 https://doi.org/10.5194/gmd-9-1937-2016	journal	January 2016
Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables Hengl, Tomislav; Nussbaum, Madlene; Wright, Marvin N. PeerJ, Vol. 6 https://doi.org/10.7717/peerj.5518	journal	January 2018

Similar Records

Arctic Tipping Points Triggering Global Change (LDRD Final Report)

Technical Report · Tue Sep 01 00:00:00 EDT 2020 · OSTI ID:1669210

An evaluation of the E3SMv1 Arctic ocean and sea-ice regionally refined model

Journal Article · Tue Apr 12 00:00:00 EDT 2022 · Geoscientific Model Development (Online) · OSTI ID:1869602

The DOE E3SM version 2.1: overview and assessment of the impacts of parameterized ocean submesoscales

Journal Article · Tue Mar 11 00:00:00 EDT 2025 · Geoscientific Model Development (Online) · OSTI ID:2538336

Related Subjects

54 ENVIRONMENTAL SCIENCES
arctic
climate
energy exascale earth system model
machine learning

Machine learning feature analysis illuminates disparity between E3SM climate models and observed climate change

Citation Formats

References (16)

Similar Records

Related Subjects