气候变化领域集成服务门户(CCPortal): Downscaling Daily Reference Evapotranspiration Using a Super-Resolution Convolutional Transposed Network

CCPortal

DOI	10.3390/w16020335
	Downscaling Daily Reference Evapotranspiration Using a Super-Resolution Convolutional Transposed Network
	Liu, Yong; Yan, Xiaohui; Du, Wenying; Zhang, Tianqi; Bai, Xiaopeng; Nan, Ruichuan
发表日期	2024
EISSN	2073-4441
起始页码	16
结束页码	2
卷号	16 期号:2
英文摘要	The current work proposes a novel super-resolution convolutional transposed network (SRCTN) deep learning architecture for downscaling daily climatic variables. The algorithm was established based on a super-resolution convolutional neural network with transposed convolutions. This study designed synthetic experiments to downscale daily reference evapotranspiration (ET0) data, which are a key indicator for climate change, from low resolutions (2 degrees, 1 degrees, and 0.5 degrees) to a fine resolution (0.25 degrees). The entire time period was divided into two major parts, i.e., training-validation (80%) and test periods (20%), and the training-validation period was further divided into training (80%) and validation (20%) parts. In the comparison of the downscaling performance between the SRCTN and Q-M models, the root-mean-squared error (RMSE) values indicated the accuracy of the models. For the SRCTN model, the RMSE values were reported for different scaling ratios: 0.239 for a ratio of 8, 0.077 for a ratio of 4, and 0.015 for a ratio of 2. In contrast, the RMSE values for the Q-M method were 0.334, 0.208, and 0.109 for scaling ratios of 8, 4, and 2, respectively. Notably, the RMSE values in the SRCTN model were consistently lower than those in the Q-M method across all scaling ratios, suggesting that the SRCTN model exhibited better downscaling performance in this evaluation. The results exhibited that the SRCTN method could reproduce the spatiotemporal distributions and extremes for the testing period very well. The trained SRCTN model in one study area performed remarkably well in a different area via transfer learning without re-training or calibration, and it outperformed the classic downscaling approach. The good performance of the SRCTN algorithm can be primarily attributed to the incorporation of transposed convolutions, which can be partially seen as trainable upsampling operations. Therefore, the proposed SRCTN method is a promising candidate tool for downscaling daily ET0 and can potentially be employed to conduct downscaling operations for other variables.
英文关键词	evapotranspiration; super resolution; convolutional neural network; downscaling
语种	英语
WOS研究方向	Environmental Sciences & Ecology ; Water Resources
WOS类目	Environmental Sciences ; Water Resources
WOS记录号	WOS:001151328200001
来源期刊	WATER
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/303849
作者单位	China University of Geosciences; Dalian University of Technology
推荐引用方式 GB/T 7714	Liu, Yong,Yan, Xiaohui,Du, Wenying,et al. Downscaling Daily Reference Evapotranspiration Using a Super-Resolution Convolutional Transposed Network[J],2024,16(2).
APA	Liu, Yong,Yan, Xiaohui,Du, Wenying,Zhang, Tianqi,Bai, Xiaopeng,&Nan, Ruichuan.(2024).Downscaling Daily Reference Evapotranspiration Using a Super-Resolution Convolutional Transposed Network.WATER,16(2).
MLA	Liu, Yong,et al."Downscaling Daily Reference Evapotranspiration Using a Super-Resolution Convolutional Transposed Network".WATER 16.2(2024).