Machine Learning Predictions of a Multiresolution Climate Model Ensemble

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. We also find that global annually averaged precipitation is more sensitive to resolution changes than to any of the model parameters considered.

[1]  George C. Runger,et al.  Feature Selection with Ensembles, Artificial Variables, and Redundancy Elimination , 2009, J. Mach. Learn. Res..

[2]  Mrinal K. Sen,et al.  Error Reduction and Convergence in Climate Prediction , 2008 .

[3]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[6]  Earth's Global Energy Budget , 2009 .

[7]  Richard A. Marcum,et al.  Application of deep convolutional neural networks to automatic feature/object detection in high resolution remote sensing imagery , 2017 .

[8]  Marie-Alice Foujols,et al.  Impact of the LMDZ atmospheric grid configuration on the climate and sensitivity of the IPSL-CM5A coupled model , 2013, Climate Dynamics.

[9]  Michael Goldstein,et al.  Fast linked analyses for scenario‐based hierarchies , 2012 .

[10]  Michael Goldstein,et al.  Small Sample Bayesian Designs for Complex High-Dimensional Models Based on Information Gained Using Fast Approximations , 2009, Technometrics.

[11]  Sally A. McFarlane,et al.  Uncertainty quantification and parameter tuning in the CAM5 Zhang‐McFarlane convection scheme and impact of improved convection on the global circulation and climate , 2012 .

[12]  Hui Wan,et al.  Short ensembles: an efficient method for discerning climate-relevant sensitivities in atmospheric general circulation models , 2014 .

[13]  S. E. Haupt,et al.  Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather , 2017 .

[14]  Richard Neale,et al.  Parametric sensitivity analysis of precipitation at global and local scales in the Community Atmosphere Model CAM5 , 2015 .

[15]  Peter Z. G. Qian,et al.  Bayesian Hierarchical Modeling for Integrating Low-Accuracy and High-Accuracy Experiments , 2008, Technometrics.

[16]  L. Ruby Leung,et al.  Sensitivity of U.S. summer precipitation to model resolution and convective parameterizations across gray zone resolutions , 2017 .

[17]  W. Collins,et al.  Description of the NCAR Community Atmosphere Model (CAM 3.0) , 2004 .

[18]  Leonard A. Smith,et al.  Uncertainty in predictions of the climate response to rising levels of greenhouse gases , 2005, Nature.

[19]  Derek Bingham,et al.  Prediction and Computer Model Calibration Using Outputs From Multifidelity Simulators , 2012, Technometrics.

[20]  Prabhat,et al.  Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets , 2016, ArXiv.

[21]  Andrew Gettelman,et al.  The Art and Science of Climate Model Tuning , 2017 .

[22]  Katherine J. Evans,et al.  Exploring an Ensemble-Based Approach to Atmospheric Climate Modeling and Testing at Scale , 2017, ICCS.

[23]  Donald D. Lucas,et al.  The parametric sensitivity of CAM5's MJO , 2014 .

[24]  R. A. Miller,et al.  Sequential kriging optimization using multiple-fidelity evaluations , 2006 .

[25]  Andrei P. Sokolov,et al.  Quantifying Uncertainties in Climate System Properties with the Use of Recent Climate Observations , 2002, Science.

[26]  Malte Prieß,et al.  Surrogate-based optimization of climate model parameters using response correction , 2011, J. Comput. Sci..

[27]  M. Webb,et al.  Quantification of modelling uncertainties in a large ensemble of climate change simulations , 2004, Nature.

[28]  W. Collins,et al.  The Community Earth System Model: A Framework for Collaborative Research , 2013 .

[29]  Claire Monteleoni,et al.  Tracking climate models , 2011, CIDU.

[30]  James E. Campbell,et al.  An Approach to Sensitivity Analysis of Computer Models: Part I—Introduction, Input Variable Selection and Preliminary Variable Assessment , 1981 .

[31]  Donald D. Lucas,et al.  Failure analysis of parameter-induced simulation crashes in climate models , 2013 .

[32]  A. O'Hagan,et al.  Predicting the output from a complex computer code when fast approximations are available , 2000 .