Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing

Accurate and timely flood forecasting, facilitated by remote sensing technology, is crucial to mitigate the damage and loss of life caused by floods. However, despite years of research, accurate flood prediction still faces numerous challenges, including complex spatiotemporal features and varied fl...

Full description

Bibliographic Details
Main Authors: Jiange Jiang, Chen Chen, Yang Zhou, Stefano Berretti, Lei Liu, Qingqi Pei, Jianming Zhou, Shaohua Wan
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10380452/
_version_ 1797348759138467840
author Jiange Jiang
Chen Chen
Yang Zhou
Stefano Berretti
Lei Liu
Qingqi Pei
Jianming Zhou
Shaohua Wan
author_facet Jiange Jiang
Chen Chen
Yang Zhou
Stefano Berretti
Lei Liu
Qingqi Pei
Jianming Zhou
Shaohua Wan
author_sort Jiange Jiang
collection DOAJ
description Accurate and timely flood forecasting, facilitated by remote sensing technology, is crucial to mitigate the damage and loss of life caused by floods. However, despite years of research, accurate flood prediction still faces numerous challenges, including complex spatiotemporal features and varied flood patterns influenced by multiple variables. Moreover, long-term flood forecasting is always tricky due to the constantly changing conditions of the surrounding environment. In this study, we propose a heterogeneous dynamic temporal graph convolutional network (HD-TGCN) for flood forecasting. Specifically, we designed a dynamic temporal graph convolution module (D-TGCM) to generate a dynamic adjacency matrix by incorporating a multihead self-attention mechanism, enabling our model to capture the dynamic spatiotemporal features of flood data by utilizing temporal graph convolution operations on the dynamic matrix. Furthermore, to reflect the impact of multiple meteorological and hydrological features on the heterogeneity of flood data, we propose a novel approach that utilizes multiple parallel D-TGCMs for processing heterogeneous graph data and implements a fusion mechanism to capture varied flood patterns influenced by multiple variables. Experiments conducted on a real dataset in Wuyuan County, Jiangxi Province, demonstrate that the HD-TGCN outperforms the state-of-the-art flood prediction models in mean absolute error, Nash–Sutcliffe efficiency, and root-mean-square error, with improvements of 80.32%, 0.15%, and 73.99%, respectively, providing a more accurate flood forecasting method that will play a critical role in future flood disaster prevention and control.
first_indexed 2024-03-08T12:10:36Z
format Article
id doaj.art-5cb13d757cfc449f9bb32f4a0206bd00
institution Directory Open Access Journal
issn 2151-1535
language English
last_indexed 2024-03-08T12:10:36Z
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj.art-5cb13d757cfc449f9bb32f4a0206bd002024-01-23T00:00:22ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01173108312210.1109/JSTARS.2023.334916210380452Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote SensingJiange Jiang0https://orcid.org/0000-0003-2644-3224Chen Chen1https://orcid.org/0000-0002-4971-5029Yang Zhou2https://orcid.org/0009-0001-6603-3580Stefano Berretti3https://orcid.org/0000-0003-1219-4386Lei Liu4https://orcid.org/0000-0001-8173-0408Qingqi Pei5https://orcid.org/0000-0001-7601-5434Jianming Zhou6https://orcid.org/0000-0002-4971-5029Shaohua Wan7https://orcid.org/0000-0001-7013-9081School of Telecommunications Engineering, Xidian University, Xi'an, ChinaSchool of Telecommunications Engineering, Xidian University, Xi'an, ChinaMinistry of Water Resources of China, Beijing, ChinaDepartment of Information Engineering, University of Florence, Florence, ItalySchool of Telecommunications Engineering, Xidian University, Xi'an, ChinaSchool of Telecommunications Engineering, Xidian University, Xi'an, ChinaChina Unicom Shenzhen Branch, Shenzhen, ChinaShenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, ChinaAccurate and timely flood forecasting, facilitated by remote sensing technology, is crucial to mitigate the damage and loss of life caused by floods. However, despite years of research, accurate flood prediction still faces numerous challenges, including complex spatiotemporal features and varied flood patterns influenced by multiple variables. Moreover, long-term flood forecasting is always tricky due to the constantly changing conditions of the surrounding environment. In this study, we propose a heterogeneous dynamic temporal graph convolutional network (HD-TGCN) for flood forecasting. Specifically, we designed a dynamic temporal graph convolution module (D-TGCM) to generate a dynamic adjacency matrix by incorporating a multihead self-attention mechanism, enabling our model to capture the dynamic spatiotemporal features of flood data by utilizing temporal graph convolution operations on the dynamic matrix. Furthermore, to reflect the impact of multiple meteorological and hydrological features on the heterogeneity of flood data, we propose a novel approach that utilizes multiple parallel D-TGCMs for processing heterogeneous graph data and implements a fusion mechanism to capture varied flood patterns influenced by multiple variables. Experiments conducted on a real dataset in Wuyuan County, Jiangxi Province, demonstrate that the HD-TGCN outperforms the state-of-the-art flood prediction models in mean absolute error, Nash–Sutcliffe efficiency, and root-mean-square error, with improvements of 80.32%, 0.15%, and 73.99%, respectively, providing a more accurate flood forecasting method that will play a critical role in future flood disaster prevention and control.https://ieeexplore.ieee.org/document/10380452/Deep learningdynamic graph convolutionflood forecastingmultivariable predictionspatiotemporal graph data
spellingShingle Jiange Jiang
Chen Chen
Yang Zhou
Stefano Berretti
Lei Liu
Qingqi Pei
Jianming Zhou
Shaohua Wan
Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning
dynamic graph convolution
flood forecasting
multivariable prediction
spatiotemporal graph data
title Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing
title_full Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing
title_fullStr Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing
title_full_unstemmed Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing
title_short Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing
title_sort heterogeneous dynamic graph convolutional networks for enhanced spatiotemporal flood forecasting by remote sensing
topic Deep learning
dynamic graph convolution
flood forecasting
multivariable prediction
spatiotemporal graph data
url https://ieeexplore.ieee.org/document/10380452/
work_keys_str_mv AT jiangejiang heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT chenchen heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT yangzhou heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT stefanoberretti heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT leiliu heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT qingqipei heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT jianmingzhou heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing
AT shaohuawan heterogeneousdynamicgraphconvolutionalnetworksforenhancedspatiotemporalfloodforecastingbyremotesensing