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

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.

• Publication year

  2025

• Venue

  Journal of Environmental Management

• Publication date

  2025-03-17

• Fields of study

  Medicine, Environmental Science

• Identifiers
  DOI 10.1016/j.jenvman.2025.124969PMID 40101483
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• A new Bayesian semi-supervised active learning framework for large-scale crop mapping using Sentinel-2 imagery

  2024cited by this paper
• Transfer learning in environmental remote sensing

  2024cited by this paper
• Spatiotemporal Pattern, Evolutionary Trend, and Driving Forces Analysis of Ecological Quality in the Irtysh River Basin (2000–2020)

  2024cited by this paper
• Monitoring inland water via Sentinel satellite constellation: A review and perspective

  2023cited by this paper
• Linking soil phosphorus availability and phosphatase functional genes to coastal marsh erosion: Implications for nutrient cycling and wetland restoration.

  2023cited by this paper
• Evaluation of Copernicus DEM and Comparison to the DEM Used for Landsat Collection-2 Processing

  2023cited by this paper
• National hydrologic connectivity classification links wetlands with stream water quality

  2023cited by this paper
• Influence of human activities and climate change on wetland landscape pattern-A review.

  2023cited by this paper
• Dynamic Assessment and Sustainability Strategies of Ecological Security in the Irtysh River Basin of Xinjiang, China

  2023cited by this paper
• Extensive global wetland loss over the past three centuries

  2023cited by this paper
• Rapid and large changes in coastal wetland structure in China's four major river deltas

  2023cited by this paper
• Evaluation of Remote Sensing Products for Wetland Mapping in the Irtysh River Basin

  2023cited by this paper
• GWL_FCS30: a global 30 m wetland map with a fine classification system using multi-sourced and time-series remote sensing imagery in 2020

  2023cited by this paper
• Microplastics profile in constructed wetlands: Distribution, retention and implications.

  2022cited by this paper
• Tradeoffs and synergies in wetland multifunctionality: A scaling issue.

  2022cited by this paper
• Remote Sensing and Machine Learning Tools to Support Wetland Monitoring: A Meta-Analysis of Three Decades of Research

  2022cited by this paper
• Hydrology-mediated ecological function of a large wetland threatened by an invasive predator.

  2022cited by this paper
• State of the Art: High-Performance and High-Throughput Computing for Remote Sensing Big Data

  2022cited by this paper
• Monitoring spatial and temporal dynamics of wetland vegetation and their response to hydrological conditions in a large seasonal lake with time series Landsat data

  2022cited by this paper
• A state-of-the-art and future perspectives of transboundary rivers in the cold climate – a systematic review of Irtysh River

  2022cited by this paper
• Object based classification of a riparian environment using ultra-high resolution imagery, hierarchical landcover structures, and image texture

  2022cited by this paper
• Dynamic World, Near real-time global 10 m land use land cover mapping

  2022cited by this paper
• Indictors of wetland health improve following small-scale ecological restoration on private land.

  2022cited by this paper
• Spatial and temporal variation and driving factors of wetland in the Amu Darya River Delta, Central Asia

  2022cited by this paper
• Artificial wetlands as alternative habitat for a wide range of waterbird species

  2022cited by this paper
• The impacts of mangrove range expansion on wetland ecosystem services in the southeastern United States: Current understanding, knowledge gaps, and emerging research needs

  2022cited by this paper
• Wetlands, Flooding, and the Clean Water Act

  2022cited by this paper
• Impact of climate change on wetland ecosystems: A critical review of experimental wetlands.

  2021cited by this paper
• A simple and robust wetland classification approach by using optical indices, unsupervised and supervised machine learning algorithms

  2021cited by this paper
• Tracking the environmental impacts of ecological engineering on coastal wetlands with numerical modeling and remote sensing.

  2021cited by this paper
• Anthropogenic disturbances caused declines in the wetland area and carbon pool in China during the last four decades

  2021cited by this paper
• Object-Based Wetland Vegetation Classification Using Multi-Feature Selection of Unoccupied Aerial Vehicle RGB Imagery

  2021cited by this paper
• A near real-time deep learning approach for detecting rice phenology based on UAV images

  2020cited by this paper
• Anthropogenic, Direct Pressures on Coastal Wetlands

  2020cited by this paper
• UN Decade on Ecosystem Restoration 2021–2030—What Chance for Success in Restoring Coastal Ecosystems?

  2020cited by this paper
• Monitoring long-term shoreline dynamics and human activities in the Hangzhou Bay, China, combining daytime and nighttime EO data

  2020cited by this paper
• Google Earth Engine for geo-big data applications: A meta-analysis and systematic review

  2020cited by this paper
• Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations - A Review

  2020cited by this paper
• Estimation of wheat planting date using machine learning algorithms based on available climate data

  2020cited by this paper
• Euclidean distance based feature ranking and subset selection for bearing fault diagnosis

  2020cited by this paper
• Multi-Label Active Learning Algorithms for Image Classification

  2020cited by this paper
• The migration of training samples towards dynamic global land cover mapping

  2020cited by this paper
• Future impacts of climate change on inland Ramsar wetlands

  2020cited by this paper
• A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images

  2020cited by this paper
• Wetland Monitoring Using SAR Data: A Meta-Analysis and Comprehensive Review

  2020cited by this paper
• Stable classification with limited sample: transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017.

  2019cited by this paper
• Wetland biomass inversion and space differentiation: A case study of the Yellow River Delta Nature Reserve

  2019cited by this paper
• Deep learning and its applications to machine health monitoring

  2019cited by this paper
• Assessment of the effectiveness of supervised and unsupervised methods: maximizing land-cover classification accuracy with spectral indices data

  2019cited by this paper
• Spatial distribution and controlling factors of surface water stable isotope values (δ18O and δ2H) across Kazakhstan, Central Asia.

  2019cited by this paper
• Integrating LiDAR data and multi-temporal aerial imagery to map wetland inundation dynamics using Google Earth Engine.

  2019cited by this paper
• Valuating service loss of snow cover in Irtysh River Basin

  2019cited by this paper
• Diverse policies leading to contrasting impacts on land cover and ecosystem services in Northeast China

  2019cited by this paper
• Global Wetland Outlook: State of the World’s Wetlands and Their Services to People

  2018cited by this paper
• Indicators of vegetation development in restored wetlands

  2018cited by this paper
• Implementation of machine-learning classification in remote sensing: an applied review

  2018cited by this paper
• Evaluating the potential for site-specific modification of LiDAR DEM derivatives to improve environmental planning-scale wetland identification using Random Forest classification

  2018cited by this paper
• A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning

  2018cited by this paper
• Wetlands In a Changing Climate: Science, Policy and Management

  2018cited by this paper
• Contribution of climate and land cover changes to reduction in soil erosion rates within small cultivated catchments in the eastern part of the Russian Plain during the last 60 years

  2018cited by this paper
• Automated Extraction of Surface Water Extent from Sentinel-1 Data

  2018cited by this paper
• Efficient Delineation of Nested Depression Hierarchy in Digital Elevation Models for Hydrological Analysis Using Level‐Set Method

  2018cited by this paper
• Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

  2017cited by this paper
• A Review of Wetland Remote Sensing

  2017cited by this paper
• Google Earth Engine: Planetary-scale geospatial analysis for everyone

  2017cited by this paper
• Prototypical Networks for Few-shot Learning

  2017cited by this paper
• Wetlands: conservation's poor cousins

  2016cited by this paper
• High-resolution mapping of global surface water and its long-term changes

  2016cited by this paper
• Earth's surface water change over the past 30 years

  2016cited by this paper
• Random forest in remote sensing: A review of applications and future directions

  2016cited by this paper
• Integrated time‐lapse geoelectrical imaging of wetland hydrological processes

  2016cited by this paper
• Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances

  2016cited by this paper
• Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art

  2016cited by this paper
• Optimizations on supply and distribution of dissolved oxygen in constructed wetlands: A review.

  2016cited by this paper
• Global land cover mapping at 30 m resolution: A POK-based operational approach

  2015cited by this paper
• Object-Based Image Analysis in Wetland Research: A Review

  2015cited by this paper
• Remote sensing of inland waters: Challenges, progress and future directions

  2015cited by this paper
• Water management: Current and future challenges and research directions

  2015cited by this paper
• Towards a common validation sample set for global land-cover mapping

  2014cited by this paper
• Wetland inundation mapping and change monitoring using Landsat and airborne LiDAR data

  2014cited by this paper
• Dynamic monitoring of wetland cover changes using time-series remote sensing imagery

  2014cited by this paper
• Good practices for estimating area and assessing accuracy of land change

  2014cited by this paper
• Effects of reservoirs on seasonal discharge of Irtysh River measured by Lepage test

  2014cited by this paper
• How much wetland has the world lost? Long-term and recent trends in global wetland area

  2014cited by this paper
• Wetlands, carbon, and climate change

  2013cited by this paper
• Characterization of soil bacterial community structure and physicochemical properties in created and natural wetlands.

  2013cited by this paper
• Tidal wetland stability in the face of human impacts and sea-level rise

  2013cited by this paper
• Texture Classification from Random Features

  2012cited by this paper
• Opening the archive: How free data has enabled the science and monitoring promise of Landsat

  2012cited by this paper
• Structural and Functional Loss in Restored Wetland Ecosystems

  2012cited by this paper
• Community based mangrove management: a review on status and sustainability.

  2012cited by this paper
• Conservation management of rivers and wetlands under climate change – a synthesis

  2011cited by this paper
• Wetlands as natural assets

  2011cited by this paper
• Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review

  2010cited by this paper
• Wetlands and global climate change: the role of wetland restoration in a changing world

  2009cited by this paper
• Granger causality and transfer entropy are equivalent for Gaussian variables.

  2009cited by this paper
• Decline of wetland ecosystems in the coastal plain of Israel during the 20th century: Implications for wetland conservation and management

  2009cited by this paper
• Development of a two-band enhanced vegetation index without a blue band

  2008cited by this paper
• The Application of RS in Wetland Ecosystem Health Assessment: A Case Study of Dagu River Estuary

  2008cited by this paper
• Will the river Irtysh survive the year 2030? Impact of long-term unsuitable land use and water management of the upper stretch of the river catchment (North Kazakhstan)

  2006cited by this paper

• Vegetation Succession Dynamics and Drivers in Accretional Salt Marshes: A 34-Year Case Study in Hangzhou Bay

  2026cites this paper
• Assessing land use changes and agricultural practices in highland valley-bottom wetlands in Taita Hills, Kenya.

  2025cites this paper
• Weakly Supervised Semantic Segmentation of Mangrove Ecosystem Using Sentinel-1 SAR and Deep Convolutional Neural Networks

  2025cites this paper
• A novel method integrating sample migration and threshold optimization for high-precision greenhouse classification: evidence from Southern China

  2025cites this paper
• Spatiotemporal characteristics and driving factors of the fractional vegetation coverage in the Ertix River Basin

  2025cites this paper
• Integrative analysis of transboundary land use conflicts in the Aral Sea Basin: A multi-scale assessment of drivers and strategies for sustainable management

  2025cites this paper
• Research on Wetland Fine Classification Based on Remote Sensing Images with Multi-Temporal and Feature Optimization

  2025cites this paper
• High-resolution spatiotemporal analysis and driver attribution of floods in Kazakhstan using SHAP and remote sensing integration

  2025cites this paper
• Fine Identification of Lake Water Bodies and Near-Water Land Using Multi-Source Remote Sensing Fusion: A Case Study of Weishan Lake, China

  2025cites this paper
• Dynamics of coastal wetlands and their impacts on migratory bird habitats in China-Southeast Asia-South Asia

  2025cites this paper