Monitoring of Oil Spill Risk in Coastal Areas Based on Polarimetric SAR Satellite Images and Deep Learning Theory

被引:5
|
作者
Liao, Lu [1 ,2 ]
Zhao, Qing [1 ]
Song, Wenyue [3 ]
机构
[1] Univ Elect Sci & Technol China, Sch Resources & Environm, Chengdu 611731, Peoples R China
[2] Sichuan Bur Surveying Mapping & Geoinformat, Technol Serv Ctr Surveying & Mapping, Chengdu 610081, Peoples R China
[3] Anhui Univ, Sch Resources & Environm Engn, Hefei 230601, Peoples R China
关键词
oil film; water pollution; remote sensing; coastal area; deep learning; CLASSIFICATION;
D O I
10.3390/su151914504
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Healthy coasts have a high ecological service value. However, many coastal areas are faced with oil spill risks. The Synthetic Aperture Radar (SAR) remote sensing technique has become an effective tool for monitoring the oil spill risk in coastal areas. In this study, taking Jiaozhou Bay in China as the study area, an innovative oil spill monitoring framework was established based on Polarimetric SAR (PolSAR) images and deep learning theory. Specifically, a DeepLabv3+-based semantic segmentation model was trained using 35 Sentinel-1 satellite images of oil films on the sea surface from maritime sectors in different regions all over the world, which not only considered the information from the PolSAR images but also meteorological conditions; then, the well-trained framework was deployed to identify the oil films in the Sentinel-1 images of Jiaozhou Bay from 2017 to 2019. The experimental results show that the detection accuracies of the proposed oil spill detection model were higher than 0.95. It was found that the oil films in Jiaozhou Bay were mainly concentrated in the vicinity of the waterways and coastal port terminals, that the occurrence frequency of oil spills in Jiaozhou Bay decreased from 2017 to 2019, and that more than 80 percent of the oil spill events occurred at night, mainly coming from the illegal discharge of waste oil from ships. These data indicate that, in the future, the PolSAR technique will play a more important role in oil spill monitoring for Jiaozhou Bay due to its capability to capture images at night.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] A method for coastal oil tank detection in polarimetric SAR images based on recognition of T-shaped harbor
    LIU Chun
    XIE Chunhua
    YANG Jian
    XIAO Yingying
    BAO Junliang
    JournalofSystemsEngineeringandElectronics, 2018, 29 (03) : 499 - 509
  • [32] Oil Spill Detection Algorithm of a Fully Polarimetric SAR Based on Dual-EndNet
    Song Dongmei
    Wang Mingyue
    Hu Chengcong
    Zhang Jie
    Wang Bin
    Liu Shanwei
    Wang Dawei
    Liu Bin
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (24)
  • [33] Oil Spill Identification from Satellite Images Using Deep Neural Networks
    Krestenitis, Marios
    Orfanidis, Georgios
    Ioannidis, Konstantinos
    Avgerinakis, Konstantinos
    Vrochidis, Stefanos
    Kompatsiaris, Ioannis
    REMOTE SENSING, 2019, 11 (15)
  • [34] Introduction of infomax learning algorithm and application for oil spill detection in SAR images
    Obi, Shinzo
    Okajima, Kenji
    Koizumi, Yoshinori
    Murata, Minoru
    IEEJ Transactions on Fundamentals and Materials, 2006, 126 (06) : 496 - 503
  • [35] Oil Spill Detection in Quad-Polarimetric SAR Images Using an Advanced Convolutional Neural Network Based on SuperPixel Model
    Zhang, Jin
    Feng, Hao
    Luo, Qingli
    Li, Yu
    Wei, Jujie
    Li, Jian
    REMOTE SENSING, 2020, 12 (06)
  • [36] POLARIMETRIC SAR IMAGES CLASSIFICATION USING DEEP BELIEF NETWORKS WITH LEARNING FEATURES
    Hou, Biao
    Luo, Xiaohuan
    Wang, Shuang
    Jiao, Licheng
    Zhang, Xiangrong
    2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 2366 - 2369
  • [37] Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images
    Chen, Guandong
    Li, Yu
    Sun, Guangmin
    Zhang, Yuanzhi
    APPLIED SCIENCES-BASEL, 2017, 7 (10):
  • [38] A Deep Convolutional Neural Network for Oil Spill Detection from Spaceborne SAR Images
    Zeng, Kan
    Wang, Yixiao
    REMOTE SENSING, 2020, 12 (06)
  • [39] Model-based processing of multifrequency polarimetric SAR images of urban areas
    Pellizzeri, TM
    Lombardo, P
    2ND GRSS/ISPRS JOINT WORKSHOP ON REMOTE SENSING AND DATA FUSION OVER URBAN AREAS, 2003, : 47 - 51
  • [40] A self-evolving deep learning algorithm for automatic oil spill detection in Sentinel-1 SAR images
    Li, Chenglei
    Kim, Duk-jin
    Park, Soyeon
    Kim, Junwoo
    Song, Juyoung
    REMOTE SENSING OF ENVIRONMENT, 2023, 299