CliGAN: A Structurally Sensitive Convolutional Neural Network Model for Statistical Downscaling of Precipitation from Multi-Model Ensembles

Chiranjib Chaudhuri,Colin Robertson

doi:10.3390/w12123353

Abstract

Despite numerous studies in statistical downscaling methodologies, there remains a lack of methods that can downscale from precipitation modeled in global climate models to regional level high resolution gridded precipitation. This paper reports a novel downscaling method using a Generative Adversarial Network (GAN), CliGAN, which can downscale large-scale annual maximum precipitation given by simulation of multiple atmosphere-ocean global climate models (AOGCM) from Coupled Model Inter-comparison Project 6 (CMIP6) to regional-level gridded annual maximum precipitation data. This framework utilizes a convolution encoder-dense decoder network to create a generative network and a similar network to create a critic network. The model is trained using an adversarial training approach. The critic uses the Wasserstein distance loss function and the generator is trained using a combination of adversarial loss Wasserstein distance, structural loss with the multi-scale structural similarity index (MSSIM), and content loss with the Nash-Sutcliff Model Efficiency (NS). The MSSIM index allowed us to gain insight into the model’s regional characteristics and shows that relying exclusively on point-based error functions, widely used in statistical downscaling, may not be enough to reliably simulate regional precipitation characteristics. Further use of structural loss functions within CNN-based downscaling methods may lead to higher quality downscaled climate model products.

Highlights

Despite over twenty years of studies developing statistical downscaling methodologies, there remains a lack of methods that can downscale from atmosphere-ocean global climate models (AOGCM) precipitation to regional level high resolution gridded precipitation [1,2]
We develop a novel downscaling method using Generative Adversarial Network (GAN), which can downscale an ensemble of large-scale annual maximum precipitation given by several AOGCMs to the regional-level gridded annual maximum precipitation
The median annual maximum rainfall generated by the various AOGCMs examined in this study varied considerably (Figure 3), indicating significant inter-model uncertainty and the need for an ensemble approach [73]

Summary

Introduction

Despite over twenty years of studies developing statistical downscaling methodologies, there remains a lack of methods that can downscale from AOGCM precipitation to regional level high resolution gridded precipitation [1,2]. Compared to other climate variables, such as temperature or barometric pressure, precipitation is more fragmented in space, and interactions of different atmospheric scales (local, meso, synoptic) and terrestrial features are more apparent in observed precipitation patterns. It is very difficult for continuous functions used in traditional statistical downscaling methods to simulate these types of local patterns. Defined loss functions inhibit the potential of machine learning methods in downscaling, leading to the poor performance of models at regional scales

Objectives

Methods

Results

Conclusion