A Near-Real-Time Flood Detection Method Based on Deep Learning and SAR Images

被引:13
|
作者
Wu, Xuan [1 ,2 ,3 ]
Zhang, Zhijie [4 ,5 ]
Xiong, Shengqing [5 ]
Zhang, Wanchang [1 ,2 ]
Tang, Jiakui [6 ,7 ]
Li, Zhenghao [1 ,2 ,3 ]
An, Bangsheng [1 ,2 ,3 ]
Li, Rui [1 ,2 ,3 ]
机构
[1] Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China
[2] Int Res Ctr Big Data Sustainable Dev Goals, Beijing 100094, Peoples R China
[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[4] Univ Arizona, Sch Geog Dev & Environm, Tucson, AZ 85719 USA
[5] China Geol Survey, Nat Resources Aerogeophys & Remote Sensing Ctr, Beijing 100083, Peoples R China
[6] Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
[7] Univ Chinese Acad Sci, Yanshan Earth Key Zone & Surface Flux Observat & R, Beijing 101408, Peoples R China
关键词
near-real-time flood detection; synthetic aperture radar; deep learning; convolutional neural network; Yangtze River basin; INUNDATION; NETWORK; EXTENT; EXTRACTION; DYNAMICS;
D O I
10.3390/rs15082046
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Owning to the nature of flood events, near-real-time flood detection and mapping is essential for disaster prevention, relief, and mitigation. In recent years, the rapid advancement of deep learning has brought endless possibilities to the field of flood detection. However, deep learning relies heavily on training samples and the availability of high-quality flood datasets is rather limited. The present study collected 16 flood events in the Yangtze River Basin and divided them into three categories for different purpose: training, testing, and application. An efficient methodology of dataset-generation for training, testing, and application was proposed. Eight flood events were used to generate strong label datasets with 5296 tiles as flood training samples along with two testing datasets. The performances of several classic convolutional neural network models were evaluated with those obtained datasets, and the results suggested that the efficiencies and accuracies of convolutional neural network models were obviously higher than that of the threshold method. The effects of VH polarization, VV polarization, and the involvement of auxiliary DEM on flood detection were investigated, which indicated that VH polarization was more conducive to flood detection, while the involvement of DEM has a limited effect on flood detection in the Yangtze River Basin. Convolutional neural network trained by strong datasets were used in near-real-time flood detection and mapping for the remaining eight flood events, and weak label datasets were generated to expand the flood training samples to evaluate the possible effects on deep learning models in terms of flood detection and mapping. The experiments obtained conclusions consistent with those previously made on experiments with strong datasets.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Near-Real-Time Flood Mapping Using Off-the-Shelf Models with SAR Imagery and Deep Learning
    Katiyar, Vaibhav
    Tamkuan, Nopphawan
    Nagai, Masahiko
    [J]. REMOTE SENSING, 2021, 13 (12)
  • [2] Near-Real-Time Assimilation of SAR-Derived Flood Maps for Improving Flood Forecasts
    Hostache, Renaud
    Chini, Marco
    Giustarini, Laura
    Neal, Jeffrey
    Kavetski, Dmitri
    Wood, Melissa
    Corato, Giovanni
    Pelich, Ramona-Maria
    Matgen, Patrick
    [J]. WATER RESOURCES RESEARCH, 2018, 54 (08) : 5516 - 5535
  • [3] A Deep Learning Method for Near-Real-Time Cloud and Cloud Shadow Segmentation from Gaofen-1 Images
    Khoshboresh-Masouleh, Mehdi
    Shah-Hosseini, Reza
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2020, 2020
  • [4] A real-time deep learning network for ship detection in SAR images
    Zhou, Wenxue
    Zhang, Huachun
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (02) : 1893 - 1899
  • [5] A real-time deep learning network for ship detection in SAR images
    Wenxue Zhou
    Huachun Zhang
    [J]. Signal, Image and Video Processing, 2024, 18 : 1893 - 1899
  • [6] Near-Real-Time Flood Forecasting Based on Satellite Precipitation Products
    Belabid, Nasreddine
    Zhao, Feng
    Brocca, Luca
    Huang, Yanbo
    Tan, Yumin
    [J]. REMOTE SENSING, 2019, 11 (03)
  • [7] Improvement of a Near-Real-Time Precipitation Estimation Algorithm Using Deep Learning
    Ma, Guangyi
    Zhu, Linglong
    Zhang, Yonghong
    Huang, Jie
    Sun, Yan
    Tian, Wei
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [8] AN INTEGRATED METHOD OF SHIP DETECTION AND RECOGNITION IN SAR IMAGES BASED ON DEEP LEARNING
    Hou, Zesheng
    Cui, Zongyong
    Cao, Zongjie
    Liu, Nengyuan
    [J]. IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 1225 - 1228
  • [9] Change Detection in SAR Images Based on Deep Learning
    Hatem Magdy Keshk
    Xu-Cheng Yin
    [J]. International Journal of Aeronautical and Space Sciences, 2020, 21 : 549 - 559
  • [10] Change Detection in SAR Images Based on Deep Learning
    Keshk, Hatem Magdy
    Yin, Xu-Cheng
    [J]. INTERNATIONAL JOURNAL OF AERONAUTICAL AND SPACE SCIENCES, 2020, 21 (02) : 549 - 559