An automatic classification method with weak supervision for large-scale wetland mapping in transboundary (Irtysh River) basin using Sentinel 1/ 2 imageries

被引:0
作者
Luo, Kaiyue [1 ,2 ]
Samat, Alim [1 ,5 ,6 ]
van de Voorde, Tim [3 ]
Jiang, Weiguo [4 ]
Li, Wenbo [1 ,6 ]
Abuduwaili, Jilili [1 ,5 ,6 ]
机构
[1] Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Urumqi 830011, Xinjiang, Peoples R China
[2] Xinjiang Univ, Coll Geog & Remote Sensing Sci, Urumqi 830017, Peoples R China
[3] Univ Ghent, Dept Geog, Ghent, Belgium
[4] Beijing Normal Univ, Fac Geog Sci, Beijing Key Lab Remote Sensing Environm & Digital, Beijing 100875, Peoples R China
[5] Al Farabi Kazakh Natl Univ, China Kazakhstan Joint Lab RS Technol & Applicat, Alma Ata 050012, Kazakhstan
[6] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
基金
中国国家自然科学基金;
关键词
Wetland classification; Sample transferring; Object-oriented random forest (OORF); Sentinel; 1/2; Spatiotemporal analysis; Irtysh River Basin; DIFFERENCE WATER INDEX; SURFACE-WATER; LONG-TERM; VEGETATION INDEX; CLIMATE-CHANGE; RANDOM FOREST; COVER CHANGES; MANAGEMENT; VALIDATION; ALGORITHMS;
D O I
10.1016/j.jenvman.2025.124969
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Wetlands are essential ecosystems that play a significant role in biodiversity conservation and environmental stability. Monitoring their changes is crucial for understanding ecological dynamics and informing conservation strategies, particularly those in transboundary basins. This study introduces a novel automatic classification method for mapping and detecting wetland changes in the Irtysh River Basin. Utilizing Google Earth Engine (GEE) as the primary platform, this method integrates unsupervised classification, sample transfer techniques, and object-oriented random forest (OORF) algorithms to generate accurate training samples and delineate wetlands. Using Sentinel-1 and Sentinel-2 satellite data, we created high-resolution wetland distribution maps. The process begins with unsupervised classification to identify wetland inundation zones, followed by overlaying permanent water bodies and surface depressions to refine the sample set. Sample transfer, using spectral similarity metrics with the GWL_FCS30 product, further enhances the robustness of the training data. The selected features from Sentinel-1 and Sentinel-2 data, including spectral indices, phenological parameters, and textural features, were optimized, resulting in 18 optimal features for the OORF classification. The classification achieved a high overall accuracy of 96.96%, with a sample accuracy of 98.1 %, and both User's and Producer's Accuracies consistently above 88 %. Spatiotemporal analysis of wetland changes from 2017 to 2023 revealed significant fluctuations, including a net loss of approximately 1,743.92 km2 of wetlands in the Irtysh River Basin. This study provides an effective and innovative method for large-scale wetland monitoring, offering valuable insights to support conservation and management efforts.
引用
收藏
页数:21
相关论文
共 126 条
[1]   Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review [J].
Adam, Elhadi ;
Mutanga, Onisimo ;
Rugege, Denis .
WETLANDS ECOLOGY AND MANAGEMENT, 2010, 18 (03) :281-296
[2]   Wetland Monitoring Using SAR Data: A Meta-Analysis and Comprehensive Review [J].
Adeli, Sarina ;
Salehi, Bahram ;
Mahdianpari, Masoud ;
Quackenbush, Lindi J. ;
Brisco, Brian ;
Tamiminia, Haifa ;
Shaw, Stephen .
REMOTE SENSING, 2020, 12 (14)
[3]   A simple and robust wetland classification approach by using optical indices, unsupervised and supervised machine learning algorithms [J].
Ahmed, Kazi Rifat ;
Akter, Simu ;
Marandi, Andres ;
Schuth, Christoph .
REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT, 2021, 23
[4]   Hyperspectral Image Classification Based on Deep Attention Graph Convolutional Network [J].
Bai, Jing ;
Ding, Bixiu ;
Xiao, Zhu ;
Jiao, Licheng ;
Chen, Hongyang ;
Regan, Amelia C. .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[5]   Wetlands as natural assets [J].
Barbier, Edward B. .
HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES, 2011, 56 (08) :1360-1373
[6]   Granger Causality and Transfer Entropy Are Equivalent for Gaussian Variables [J].
Barnett, Lionel ;
Barrett, Adam B. ;
Seth, Anil K. .
PHYSICAL REVIEW LETTERS, 2009, 103 (23)
[7]   Random forest in remote sensing: A review of applications and future directions [J].
Belgiu, Mariana ;
Dragut, Lucian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 :24-31
[8]   Indictors of wetland health improve following small-scale ecological restoration on private land [J].
Bentley, Shannon B. ;
Tomscha, Stephanie A. ;
Deslippe, Julie R. .
SCIENCE OF THE TOTAL ENVIRONMENT, 2022, 837
[9]   Assessment of the effectiveness of supervised and unsupervised methods: maximizing land-cover classification accuracy with spectral indices data [J].
Brendel, Andrea S. ;
Ferrelli, Federico ;
Piccolo, Maria C. ;
Perillo, Gerardo M. E. .
JOURNAL OF APPLIED REMOTE SENSING, 2019, 13 (01)
[10]   Dynamic World, Near real-time global 10 m land use land cover mapping [J].
Brown, Christopher F. ;
Brumby, Steven P. ;
Guzder-Williams, Brookie ;
Birch, Tanya ;
Hyde, Samantha Brooks ;
Mazzariello, Joseph ;
Czerwinski, Wanda ;
Pasquarella, Valerie J. ;
Haertel, Robert ;
Ilyushchenko, Simon ;
Schwehr, Kurt ;
Weisse, Mikaela ;
Stolle, Fred ;
Hanson, Craig ;
Guinan, Oliver ;
Moore, Rebecca ;
Tait, Alexander M. .
SCIENTIFIC DATA, 2022, 9 (01)