首页  >  科研动态  >  正文
科研动态
景映红(博士生)、沈焕锋的论文在JOURNAL OF HYDROLOGY 刊出
发布时间:2023-03-21 09:39:46     发布者:易真     浏览次数:

标题: An attention mechanism based convolutional network for satellite precipitation downscaling over China

作者: Jing, YH (Jing, Yinghong); Lin, LP (Lin, Liupeng); Li, XH (Li, Xinghua); Li, TW (Li, Tongwen); Shen, HF (Shen, Huanfeng)

来源出版物: JOURNAL OF HYDROLOGY : 613 文献号: 128388 DOI: 10.1016/j.jhydrol.2022.128388 子辑: B 出版年: OCT 2022

摘要: Precipitation is a key part of hydrological circulation and is a sensitive indicator of climate change. The Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) datasets are widely used for global and regional precipitation investigations. However, their local application is limited by the relatively coarse spatial resolution. Therefore, in this paper, an attention mechanism based convolutional network (AMCN) is proposed to downscale GPM IMERG monthly precipitation data from 0.1 degrees to 0.01 degrees. The proposed method is an end-to-end network, which consists of a global cross-attention module, a multi-factor cross-attention module, and a residual convolutional module, comprehensively considering the potential relationships between precipitation and complicated surface characteristics. In addition, a degradation loss function based on low-resolution precipitation is designed to physically constrain the network training, to improve the robustness of the proposed network under different time and scale variations. The experiments demonstrate that the proposed network significantly outperforms three baseline methods. Compared with in-situ measurements, the normalized root-mean-square error is decreased by 0.011-0.045 in the real-data experiment. Finally, a geographic difference analysis method is introduced to further improve the downscaled results by incorporating in-situ measurements for high-quality and fine-scale precipitation estimation.

作者关键词: Satellite precipitation; Spatial downscaling; Cross-attention; Residual convolutional module; Degradation loss

地址: [Jing, Yinghong; Lin, Liupeng; Shen, Huanfeng] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Li, Xinghua] Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430079, Peoples R China.

[Li, Tongwen] Sun Yat Sen Univ, Sch Geospatial Engn & Sci, Zhuhai 519082, Peoples R China.

通讯作者地址: Shen, HF (通讯作者)Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

电子邮件地址: yhjing@whu.edu.cn; linliupeng@whu.edu.cn; lixinghua5540@whu.edu.cn; litw8@mail.sysu.edu.cn; shenhf@whu.edu.cn


信息服务
学院网站教师登录 学院办公电话 学校信息门户登录

版权所有 © bwin·必赢(中国)唯一官方网站
地址:湖北省武汉市珞喻路129号 邮编:430079 
电话:027-68778381,68778284,68778296 传真:027-68778893    邮箱:sres@whu.edu.cn