Deep Learning for Climate Model Output Statistics

Climate models are an important tool for the assessment of prospective climate change effects but they suffer from systematic and representation errors, especially for precipitation. Model output statistics (MOS) reduce these errors by fitting the model output to observational data with machine learning. In this work, we explore the feasibility and potential of deep learning with convolutional neural networks (CNNs) for MOS. We propose the CNN architecture ConvMOS specifically designed for reducing errors in climate model outputs and apply it to the climate model REMO. Our results show a considerable reduction of errors and mostly improved performance compared to three commonly used MOS approaches.

[1]  Najeebullah Khan,et al.  Modeling climate change impacts on precipitation in arid regions of Pakistan: a non-local model output statistics downscaling approach , 2018, Theoretical and Applied Climatology.

[2]  M. Claussen,et al.  The atmospheric general circulation model ECHAM-4: Model description and simulation of present-day climate , 1996 .

[3]  Andreas Hotho,et al.  MapLUR , 2020, ACM Trans. Spatial Algorithms Syst..

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  G. Brasseur,et al.  Climate and air pollution modelling in South America with focus on megacities , 2009 .

[6]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[7]  S. Perkins.  Evaluation of the AR 4 Climate Models ’ Simulated Daily Maximum Temperature , Minimum Temperature , and Precipitation over Australia Using Probability Density Functions , 2007 .

[8]  Sangram Ganguly,et al.  DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution , 2017, KDD.

[9]  Shamsuddin Shahid,et al.  Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh , 2018, Atmospheric Research.

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  P. Jones,et al.  An Ensemble Version of the E‐OBS Temperature and Precipitation Data Sets , 2018, Journal of Geophysical Research: Atmospheres.

[12]  M. Noor,et al.  A non-local model output statistics approach for the downscaling of CMIP5 GCMs for the projection of rainfall in Peninsular Malaysia , 2019, Journal of Water and Climate Change.

[13]  U. Karstens,et al.  A comprehensive model inter-comparison study investigating the water budget during the BALTEX-PIDCAP period , 2001 .

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

[15]  R. Tibshirani,et al.  Prediction by Supervised Principal Components , 2006 .

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Sanaz Moghim,et al.  Bias Correction of Climate Modeled Temperature and Precipitation Using Artificial Neural Networks , 2017 .

[18]  P. Jones,et al.  A European daily high-resolution gridded data set of surface temperature and precipitation for 1950-2006 , 2008 .

[19]  Tido Semmler.  Der Wasser- und Energiehaushalt der arktischen Atmosphäre , 2002 .

[20]  Harri Kokkola,et al.  The regional aerosol-climate model REMO-HAM , 2012 .

[21]  J. Thepaut,et al.  The ERA‐Interim reanalysis: configuration and performance of the data assimilation system , 2011 .

[22]  Rich Caruana,et al.  Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping , 2000, NIPS.

[23]  Sven Kotlarski,et al.  A subgrid glacier parameterisation for use in regional climate modelling , 2007 .

[24]  Stefan Hagemann,et al.  An improved land surface parameter dataset for global and regional climate models , 2002 .

[25]  M. Widmann,et al.  Statistical downscaling of GCM-simulated precipitation using Model Output Statistics , 2014 .

[26]  Dean B. Gesch,et al.  New land surface digital elevation model covers the Earth , 1999 .

[27]  Dit-Yan Yeung,et al.  Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model , 2017, NIPS.

[28]  A. Pitman,et al.  Evaluation of the AR4 Climate Models’ Simulated Daily Maximum Temperature, Minimum Temperature, and Precipitation over Australia Using Probability Density Functions , 2007 .

[29]  H. Paeth.  Postprocessing of simulated precipitation for impact research in West Africa. Part I: model output statistics for monthly data , 2011 .

[30]  Paul Poli,et al.  The ERA-Interim archive, version 2.0 , 2011 .

[31]  Shamsuddin Shahid,et al.  Projection of spatial and temporal changes of rainfall in Sarawak of Borneo Island using statistical downscaling of CMIP5 models , 2017 .

[32]  N. C. Silver,et al.  Averaging Correlation Coefficients: Should Fishers z Transformation Be Used? , 1987 .

[33]  Daniela Jacob,et al.  A note to the simulation of the annual and inter-annual variability of the water budget over the Baltic Sea drainage basin , 2001 .