CASIA OpenIR  > 精密感知与控制研究中心  > 人工智能与机器学习
Inductive Spatiotemporal Graph Convolutional Networks for Short-term Quantitative Precipitation Forecasting
Yajing, Wu; Xuebing, Yang; Yongqiang, Tang; Chenyang, Zhang; Guoping, Zhang; Wensheng, Zhang
Source PublicationIEEE Transactions on Geoscience and Remote Sensing
ISSN0196-2892
2022
Volume0Issue:0Pages:0
Corresponding AuthorYang, Xuebing(yangxuebing2013@ia.ac.cn) ; Tang, Yongqiang(yongqiang.tang@ia.ac.cn)
Abstract

Short-term Quantitative Precipitation Forecasting (SQPF) using weather radar is an important but challenging problem as one must cope with inherent nonlinearity and spatiotemporal correlation in the data. In this paper, we propose a novel deep learning model, named Inductive spatiotemporal Graph Convolutional Networks (InstGCN), to overcome these issues in SQPF. The proposed InstGCN can learn a nonlinear mapping from historical radar reflectivity to future rainfall amounts, and extract informative spatiotemporal representations simultaneously. Specifically, we first provide a formal definition for formulating the SQPF problem from a graph perspective. Then, based on radar reflectivity and rain gauge observation, we propose a novel graph construction approach which utilizes a special elliptic structure to model the spatial dependency of precipitation area. Additionally, a new Node level Differential Block (Node-DB) is introduced to tackle the non-stationary temporal dependency. To execute inductive graph learning for unseen nodes, we design to decompose a whole graph into sub-graphs. We conduct extensive experiments on three real-world datasets in East China and a public weather radar dataset in the south-eastern parts of France. The experimental results confirm the advantages of InstGCN compared with several state-of-the-arts.

KeywordQuantitative precipitation forecasting graph convolutional networks (GCN) spatiotemporal model radar-rain gauge data merging
DOI10.1109/TGRS.2022.3159530
WOS KeywordRADAR ; PREDICTION ; TRACKING ; MACHINE
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Program of China[2019YFB2103100] ; National Natural Science Foundation of China[U1936206] ; National Natural Science Foundation of China[61906190] ; National Natural Science Foundation of China[41871020] ; National Natural Science Foundation of China[61976213] ; National Natural Science Foundation of China[61806202] ; National Natural Science Foundation of China[61906191]
Funding OrganizationNational Key Research and Development Program of China ; National Natural Science Foundation of China
WOS Research AreaGeochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
WOS SubjectGeochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS IDWOS:000783579800022
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Sub direction classification机器学习
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/47443
Collection精密感知与控制研究中心_人工智能与机器学习
Corresponding AuthorXuebing, Yang; Yongqiang, Tang
Affiliation1.the Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences
2.the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences
3.University of Chinese Academy of Sciences
4.the Public Meteorological Service Center of CMA
Recommended Citation
GB/T 7714
Yajing, Wu,Xuebing, Yang,Yongqiang, Tang,et al. Inductive Spatiotemporal Graph Convolutional Networks for Short-term Quantitative Precipitation Forecasting[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,0(0):0.
APA Yajing, Wu,Xuebing, Yang,Yongqiang, Tang,Chenyang, Zhang,Guoping, Zhang,&Wensheng, Zhang.(2022).Inductive Spatiotemporal Graph Convolutional Networks for Short-term Quantitative Precipitation Forecasting.IEEE Transactions on Geoscience and Remote Sensing,0(0),0.
MLA Yajing, Wu,et al."Inductive Spatiotemporal Graph Convolutional Networks for Short-term Quantitative Precipitation Forecasting".IEEE Transactions on Geoscience and Remote Sensing 0.0(2022):0.
Files in This Item: Download All
File Name/Size DocType Version Access License
2022-TGRS--Inductive(10052KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yajing, Wu]'s Articles
[Xuebing, Yang]'s Articles
[Yongqiang, Tang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yajing, Wu]'s Articles
[Xuebing, Yang]'s Articles
[Yongqiang, Tang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yajing, Wu]'s Articles
[Xuebing, Yang]'s Articles
[Yongqiang, Tang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2022-TGRS--Inductive Spatiotemporal Graph Convolutional Networks for Short-term Quantitative Precipitation Forecasting.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.