Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention
Floods have brought a great threat to the life and property of human beings. Under the premise of strengthening flood control engineering measures and following the strategic thinking of sustainable development, many achievements have been made in flood forecasting recently. However, due to the comp...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/24/5023 |
| _version_ | 1797500994425192448 |
|---|---|
| author | Chen Chen Dingbin Luan Song Zhao Zhan Liao Yang Zhou Jiange Jiang Qingqi Pei |
| author_facet | Chen Chen Dingbin Luan Song Zhao Zhan Liao Yang Zhou Jiange Jiang Qingqi Pei |
| author_sort | Chen Chen |
| collection | DOAJ |
| description | Floods have brought a great threat to the life and property of human beings. Under the premise of strengthening flood control engineering measures and following the strategic thinking of sustainable development, many achievements have been made in flood forecasting recently. However, due to the complexity of the traditional lumped model and distributed model, the hydrologic parameter calibration process is full of difficulties, leading to a long development cycle of a reasonable hydrologic prediction model. Even for modern data-driven models, the spatial distribution characteristics of the rainfall data are also not fully mined. Based on this situation, this paper abstracts the rainfall data into the graph structure data, uses remote sensing images to extract the elevation information, introduces the graph attention mechanism to extract the spatial characteristics of rainfall, and employs long-term and short-term memory (LSTM) network to fuse the spatial and temporal characteristics for flood prediction. Through well-designed experiments, the forecasting effect of flood peak value and flood arrival time is verified. Furthermore, compared with the LSTM model and BIGRU model without spatial feature extraction, the advantages of spatiotemporal feature fusion are highlighted. The specific performance is that the RMSE (the root means square error) and <inline-formula><math display="inline" xmlns="http://www.w3.org/1998/Math/MathML"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> (coefficient of determination) of the GA-RNN model have been significantly improved. Finally, we conduct experiments on the observed ten rainfall events in the history of the target watershed. According to the hydrological prediction specifications, the model can be evaluated as a Class B flood forecasting model. |
| first_indexed | 2024-03-10T03:11:53Z |
| format | Article |
| id | doaj.art-b54bb7dea4aa4686bfb9ace78fb0b64b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:11:53Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b54bb7dea4aa4686bfb9ace78fb0b64b2023-11-23T10:23:45ZengMDPI AGRemote Sensing2072-42922021-12-011324502310.3390/rs13245023Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph AttentionChen Chen0Dingbin Luan1Song Zhao2Zhan Liao3Yang Zhou4Jiange Jiang5Qingqi Pei6State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, ChinaMinistry of Water Resources of China, Beijing 100083, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, ChinaFloods have brought a great threat to the life and property of human beings. Under the premise of strengthening flood control engineering measures and following the strategic thinking of sustainable development, many achievements have been made in flood forecasting recently. However, due to the complexity of the traditional lumped model and distributed model, the hydrologic parameter calibration process is full of difficulties, leading to a long development cycle of a reasonable hydrologic prediction model. Even for modern data-driven models, the spatial distribution characteristics of the rainfall data are also not fully mined. Based on this situation, this paper abstracts the rainfall data into the graph structure data, uses remote sensing images to extract the elevation information, introduces the graph attention mechanism to extract the spatial characteristics of rainfall, and employs long-term and short-term memory (LSTM) network to fuse the spatial and temporal characteristics for flood prediction. Through well-designed experiments, the forecasting effect of flood peak value and flood arrival time is verified. Furthermore, compared with the LSTM model and BIGRU model without spatial feature extraction, the advantages of spatiotemporal feature fusion are highlighted. The specific performance is that the RMSE (the root means square error) and <inline-formula><math display="inline" xmlns="http://www.w3.org/1998/Math/MathML"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> (coefficient of determination) of the GA-RNN model have been significantly improved. Finally, we conduct experiments on the observed ten rainfall events in the history of the target watershed. According to the hydrological prediction specifications, the model can be evaluated as a Class B flood forecasting model.https://www.mdpi.com/2072-4292/13/24/5023flood forecastingremote sensingdeep learninggraph attention mechanismspace-time feature fusion |
| spellingShingle | Chen Chen Dingbin Luan Song Zhao Zhan Liao Yang Zhou Jiange Jiang Qingqi Pei Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention Remote Sensing flood forecasting remote sensing deep learning graph attention mechanism space-time feature fusion |
| title | Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention |
| title_full | Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention |
| title_fullStr | Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention |
| title_full_unstemmed | Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention |
| title_short | Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention |
| title_sort | flood discharge prediction based on remote sensed spatiotemporal features fusion and graph attention |
| topic | flood forecasting remote sensing deep learning graph attention mechanism space-time feature fusion |
| url | https://www.mdpi.com/2072-4292/13/24/5023 |
| work_keys_str_mv | AT chenchen flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention AT dingbinluan flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention AT songzhao flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention AT zhanliao flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention AT yangzhou flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention AT jiangejiang flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention AT qingqipei flooddischargepredictionbasedonremotesensedspatiotemporalfeaturesfusionandgraphattention |