Generating high-resolution climatological precipitation data using SinGAN

作     者：Yang Wang Hassan A.Karimi 

作者机构：Geoinformatics LaboratorySchool of Computing and InformationUniversity of PittsburghPittsburghUSA 

出 版 物：《Big Earth Data》 (地球大数据（英文）)

年 卷 期：2023年第7卷第1期

页      面：81-100页

核心收录：

学科分类：07[理学] 070601[理学-气象学] 0706[理学-大气科学] 

主　　题：Climate downscaling SinGAN deep learning adversarial training 

摘      要：High-resolution(HR)climate data are indispensable for studying regional climate trends,disaster prediction,and urban development planning in the face of climate ***,state-of-the-art long-term global climate simulations do not provide appropriate HR climate *** learning models are often used to obtain high-resolution climate ***,due to the fact that these models require sufficient low-resolution(LR)and HR data pairs for the training process,they cannot be applied to scenario with inadequate training *** this paper,we explore the applicability of a single image generative adversarial network(SinGAN)in generating HR climate *** relies on single LR input data to obtain the corresponding HR *** improve the performance for extreme-value regions,we propose a SinGAN combined with the weighted patchGAN discriminator(WSinGAN).The proposed WSinGAN outperforms comparable models in generating HR precipitation data,and its results are close to real HR data with sharp gradients and more refined small-scale *** also test the scalability of the pre-trained WSinGAN for unseen samples and show that although only a single LR sample is used to train WSinGAN,it can still produce reliable HR data for unseen data.