Spatio-temporal heterogeneous graph using multivariate earth observation time series: Application for drought forecasting
文献类型:期刊论文
作者 | Balti, Hanen2,3; Ben Abbes, Ali3; Sang, Yanfang1,4; Mellouli, Nedra2,5; Farah, Imed Riadh3 |
刊名 | COMPUTERS & GEOSCIENCES |
出版日期 | 2023-10-01 |
卷号 | 179页码:13 |
ISSN号 | 0098-3004 |
关键词 | Heterogeneous graphs Spatiotemporal data Multivariate time series Earth observation data Drought forecasting |
DOI | 10.1016/j.cageo.2023.105435 |
通讯作者 | Balti, Hanen(hanen.balti@ensi-uma.tn) |
英文摘要 | Accurate forecasting is required for the effective risk management of drought disasters. Many machine learning and deep learning-based models have been proposed for drought forecasting, however, they cannot handle the temporal and/or spatial dependencies in the input data, causing unexpected forecasting results. In order to solve the challenging issue, in this paper we proposed the Heterogeneous Spatio-Temporal Graph (HetSPGraph), for drought forecasting. It includes three major layers: spatial aggregations including inter and intra aggregations, temporal aggregation, and a forecasting network. The main function of HetSPGraph is to learn the dynamic spatiotemporal correlations between the regions and to further predict the drought in different regions, based on which accurate drought forecasting can be achieved. Experimental forecasting results of the Standardized Precipitation Evapotranspiration Index (SPEI) in China indicated that the HetSPGraph model outperformed the traditional baseline methods including the Long Short-Term Memory model (LSTM), Convolutional Neural Network-LSTM (CNN-LSTM), Gated Recurrent Unit (GRU), Spatio-Temporal Graph Convolutional Networks (STGCN) and Geographic-Semantic-Temporal Hypergraph Convolutional Network (GST-HCN). Even for long-term forecasting (12 months), more accurate forecasting results, with the coefficient of determination R2 higher than 0.89, can also be obtained by HetSPGraph compared to the other three models. The proposed HetSPGraph model has the potential for wider use in forecasting drought and other natural disasters. |
WOS关键词 | PREDICTION ; SPI ; CHALLENGES ; CHINA |
资助项目 | National Key Ramp;D Pro-gram of China[2022YFC3002804] ; National Natural Science Foundation of China[41971040] |
WOS研究方向 | Computer Science ; Geology |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:001069388900001 |
资助机构 | National Key Ramp;D Pro-gram of China ; National Natural Science Foundation of China |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/197933] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Balti, Hanen |
作者单位 | 1.Minist Emergency Management China, Key Lab Cpd & Chained Nat Hazards, Beijing 100085, Peoples R China 2.Leonard Vinci Pole Univ, Res Ctr Paris La Defense, Courbevoie, La Defense, France 3.Univ Manouba, Natl Sch Comp Sci, RIADI Lab, Manouba 2010, Tunisia 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Water Cycle & Related Land Surface Proc, Beijing 100101, Peoples R China 5.Paris 8 Univ, Lab Intelligence Artificielle & Semant Donnees LIA, F-93200 St Denis, France |
推荐引用方式 GB/T 7714 | Balti, Hanen,Ben Abbes, Ali,Sang, Yanfang,et al. Spatio-temporal heterogeneous graph using multivariate earth observation time series: Application for drought forecasting[J]. COMPUTERS & GEOSCIENCES,2023,179:13. |
APA | Balti, Hanen,Ben Abbes, Ali,Sang, Yanfang,Mellouli, Nedra,&Farah, Imed Riadh.(2023).Spatio-temporal heterogeneous graph using multivariate earth observation time series: Application for drought forecasting.COMPUTERS & GEOSCIENCES,179,13. |
MLA | Balti, Hanen,et al."Spatio-temporal heterogeneous graph using multivariate earth observation time series: Application for drought forecasting".COMPUTERS & GEOSCIENCES 179(2023):13. |
入库方式: OAI收割
来源:地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。