skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine Learning Predictions of a Multiresolution Climate Model Ensemble

Abstract

Statistical models of high-resolution climate models are useful for many purposes, including sensitivity and uncertainty analyses, but building them can be computationally prohibitive. We generated a unique multiresolution perturbed parameter ensemble of a global climate model. We use a novel application of a machine learning technique known as random forests to train a statistical model on the ensemble to make high-resolution model predictions of two important quantities: global mean top-of-atmosphere energy flux and precipitation. The random forests leverage cheaper low-resolution simulations, greatly reducing the number of high-resolution simulations required to train the statistical model. We demonstrate that high-resolution predictions of these quantities can be obtained by training on an ensemble that includes only a small number of high-resolution simulations. Finally, we also find that global annually averaged precipitation is more sensitive to resolution changes than to any of the model parameters considered.

Authors:
ORCiD logo [1]; ORCiD logo [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1488815
Report Number(s):
LLNL-JRNL-744178
Journal ID: ISSN 0094-8276; 899191
Grant/Contract Number:  
AC52-07NA27344
Resource Type:
Accepted Manuscript
Journal Name:
Geophysical Research Letters
Additional Journal Information:
Journal Volume: 45; Journal Issue: 9; Journal ID: ISSN 0094-8276
Publisher:
American Geophysical Union
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES

Citation Formats

Anderson, Gemma J., and Lucas, Donald D. Machine Learning Predictions of a Multiresolution Climate Model Ensemble. United States: N. p., 2018. Web. doi:10.1029/2018GL077049.
Anderson, Gemma J., & Lucas, Donald D. Machine Learning Predictions of a Multiresolution Climate Model Ensemble. United States. doi:10.1029/2018GL077049.
Anderson, Gemma J., and Lucas, Donald D. Thu . "Machine Learning Predictions of a Multiresolution Climate Model Ensemble". United States. doi:10.1029/2018GL077049. https://www.osti.gov/servlets/purl/1488815.
@article{osti_1488815,
title = {Machine Learning Predictions of a Multiresolution Climate Model Ensemble},
author = {Anderson, Gemma J. and Lucas, Donald D.},
abstractNote = {Statistical models of high-resolution climate models are useful for many purposes, including sensitivity and uncertainty analyses, but building them can be computationally prohibitive. We generated a unique multiresolution perturbed parameter ensemble of a global climate model. We use a novel application of a machine learning technique known as random forests to train a statistical model on the ensemble to make high-resolution model predictions of two important quantities: global mean top-of-atmosphere energy flux and precipitation. The random forests leverage cheaper low-resolution simulations, greatly reducing the number of high-resolution simulations required to train the statistical model. We demonstrate that high-resolution predictions of these quantities can be obtained by training on an ensemble that includes only a small number of high-resolution simulations. Finally, we also find that global annually averaged precipitation is more sensitive to resolution changes than to any of the model parameters considered.},
doi = {10.1029/2018GL077049},
journal = {Geophysical Research Letters},
number = 9,
volume = 45,
place = {United States},
year = {2018},
month = {4}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 6 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Error Reduction and Convergence in Climate Prediction
journal, December 2008

  • Jackson, Charles S.; Sen, Mrinal K.; Huerta, Gabriel
  • Journal of Climate, Vol. 21, Issue 24
  • DOI: 10.1175/2008JCLI2112.1

Uncertainty in predictions of the climate response to rising levels of greenhouse gases
journal, January 2005

  • Stainforth, D. A.; Aina, T.; Christensen, C.
  • Nature, Vol. 433, Issue 7024
  • DOI: 10.1038/nature03301

The Community Earth System Model: A Framework for Collaborative Research
journal, September 2013

  • Hurrell, James W.; Holland, M. M.; Gent, P. R.
  • Bulletin of the American Meteorological Society, Vol. 94, Issue 9
  • DOI: 10.1175/BAMS-D-12-00121.1

Short ensembles: an efficient method for discerning climate-relevant sensitivities in atmospheric general circulation models
journal, January 2014


Sequential kriging optimization using multiple-fidelity evaluations
journal, May 2006

  • Huang, D.; Allen, T. T.; Notz, W. I.
  • Structural and Multidisciplinary Optimization, Vol. 32, Issue 5
  • DOI: 10.1007/s00158-005-0587-0

Extremely randomized trees
journal, March 2006


Earth's Global Energy Budget
journal, March 2009

  • Trenberth, Kevin E.; Fasullo, John T.; Kiehl, Jeffrey
  • Bulletin of the American Meteorological Society, Vol. 90, Issue 3
  • DOI: 10.1175/2008BAMS2634.1

Surrogate-based optimization of climate model parameters using response correction
journal, December 2011


Impact of the LMDZ atmospheric grid configuration on the climate and sensitivity of the IPSL-CM5A coupled model
journal, July 2012

  • Hourdin, Frédéric; Foujols, Marie-Alice; Codron, Francis
  • Climate Dynamics, Vol. 40, Issue 9-10
  • DOI: 10.1007/s00382-012-1411-3

Failure analysis of parameter-induced simulation crashes in climate models
journal, January 2013

  • Lucas, D. D.; Klein, R.; Tannahill, J.
  • Geoscientific Model Development, Vol. 6, Issue 4
  • DOI: 10.5194/gmd-6-1157-2013

Parametric sensitivity analysis of precipitation at global and local scales in the Community Atmosphere Model CAM5
journal, April 2015

  • Qian, Yun; Yan, Huiping; Hou, Zhangshuan
  • Journal of Advances in Modeling Earth Systems, Vol. 7, Issue 2
  • DOI: 10.1002/2014MS000354

The Art and Science of Climate Model Tuning
journal, March 2017

  • Hourdin, Frédéric; Mauritsen, Thorsten; Gettelman, Andrew
  • Bulletin of the American Meteorological Society, Vol. 98, Issue 3
  • DOI: 10.1175/BAMS-D-15-00135.1

Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather
journal, October 2017

  • McGovern, Amy; Elmore, Kimberly L.; Gagne, David John
  • Bulletin of the American Meteorological Society, Vol. 98, Issue 10
  • DOI: 10.1175/BAMS-D-16-0123.1

An Approach to Sensitivity Analysis of Computer Models: Part I—Introduction, Input Variable Selection and Preliminary Variable Assessment
journal, July 1981


Bayesian Hierarchical Modeling for Integrating Low-Accuracy and High-Accuracy Experiments
journal, May 2008


Random Forests
journal, January 2001


Tracking climate models
journal, July 2011

  • Monteleoni, Claire; Schmidt, Gavin A.; Saroha, Shailesh
  • Statistical Analysis and Data Mining, Vol. 4, Issue 4
  • DOI: 10.1002/sam.10126

Small Sample Bayesian Designs for Complex High-Dimensional Models Based on Information Gained Using Fast Approximations
journal, November 2009


Exploring an Ensemble-Based Approach to Atmospheric Climate Modeling and Testing at Scale
journal, January 2017


Prediction and Computer Model Calibration Using Outputs From Multifidelity Simulators
journal, November 2013


Quantification of modelling uncertainties in a large ensemble of climate change simulations
journal, August 2004

  • Murphy, James M.; Sexton, David M. H.; Barnett, David N.
  • Nature, Vol. 430, Issue 7001
  • DOI: 10.1038/nature02771

Fast linked analyses for scenario-based hierarchies
journal, May 2012

  • Williamson, Daniel; Goldstein, Michael; Blaker, Adam
  • Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 61, Issue 5
  • DOI: 10.1111/j.1467-9876.2012.01042.x

    Works referencing / citing this record:

    The Application of Machine Learning Techniques to Improve El Niño Prediction Skill
    journal, October 2019

    • Dijkstra, Henk A.; Petersik, Paul; Hernández-García, Emilio
    • Frontiers in Physics, Vol. 7
    • DOI: 10.3389/fphy.2019.00153

    The Application of Machine Learning Techniques to Improve El Niño Prediction Skill
    journal, October 2019

    • Dijkstra, Henk A.; Petersik, Paul; Hernández-García, Emilio
    • Frontiers in Physics, Vol. 7
    • DOI: 10.3389/fphy.2019.00153