Classification of Wetlands in the Liaohe Estuary Based on MRMR-RF-CV Feature Preference of Multisource Remote Sensing Images

Coastal wetland ecosystems, shaped by the interaction between ocean and land, play a pivotal role in blue carbon sequestration. Understanding the distribution and evolutionary patterns of complex wetland types is essential for advancing wetland conservation, exploring blue carbon potentials, and supporting national carbon neutrality goals. This study utilized the Google Earth Engine cloud platform alongside Sentinel-1 synthetic aperture radar data, Sentinel-2 multispectral data, digital elevation model data, and unmanned aerial vehicle data to develop a feature preference algorithm integrating the minimum redundancy maximum relevance (MRMR) and random forest (RF) methods. Using eCognition, ArcMap, and ENVI platforms, we achieved an object-oriented classification of the Liaohekou Shuangtaizi wetlands. Results revealed that: 1) The MRMR-RF optimized 40 features, ranked by importance as Sentinel-2 spectral > Sentinel-1 index > Sentinel-1 radar > topographic > Sentinel-1 texture; 2) Six sets of comparison schemes were established, and the classification scheme based on the MRMR-RF model achieved the best classification performance, with an overall accuracy of 90.89% and a Kappa coefficient of 0.9; 3) The Liaohekou Estuary wetland was predominantly composed of Phragmites australis (P.australis), shallow sea, and tidal flat, followed by cropland, rivers, breeding pools, Suaeda salsa (S.salsa), reservoirs, puddles, bare soil, and building sites as secondary components; and 4) Between 2000 and 2023, the wetland area of different types in the study area changed significantly, with the changes mainly concentrated in the coastal aquaculture areas, tidal flat areas, and S.salsa growth areas.

• Publication year

  2025

• Venue

  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Environmental Science

• Identifiers
  DOI 10.1109/JSTARS.2025.3540302
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Mangrove species mapping in coastal China using synthesized Sentinel-2 high-separability images

  2024cited by this paper
• Multi-scenario simulation of land use dynamics and ecological risk: a case study of the liaohe estuary national wetland reserve using PLUS-Markov and PSR models

  2024cited by this paper
• Imaging spectroscopy investigations in wet carbon ecosystems: A review of the literature from 1995 to 2022 and future directions

  2024cited by this paper
• Fine Extraction of Plateau Wetlands Based on a Combination of Object-Oriented Machine Learning and Ecological Rules: A Case Study of Dianchi Basin

  2024cited by this paper
• Hyperspectral indices data fusion-based machine learning enhanced by MRMR algorithm for estimating maize chlorophyll content

  2024cited by this paper
• Assessing the Effectiveness of Large-Scale Ecological Restoration Measures in the Liaohe Estuary Using a Landscape Pattern Perspective

  2024cited by this paper
• A Novel mRMR-RFE-RF Method for Enhancing Medium- and Long-Term Hydrological Forecasting: A Case Study of the Danjiangkou Basin

  2024cited by this paper
• Wetlands mapping in typical regions of South America with multi-source and multi-feature integration

  2023cited by this paper
• Remote sensing feature selection for alpine wetland classification

  2023cited by this paper
• Identifying mangroves through knowledge extracted from trained random forest models: An interpretable mangrove mapping approach (IMMA)

  2023cited by this paper
• En-MinWhale: An Ensemble Approach Based on MRMR and Whale Optimization for Cancer Diagnosis

  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
• Extraction of marsh wetland in Heilongjiang Basin based on GEE and multi-source remote sensing data

  2022cited by this paper
• Performance comparison of deep learning and machine learning methods in determining wetland water areas using EuroSAT dataset

  2021cited by this paper
• Mapping salt marsh along coastal South Carolina using U-Net

  2021cited by this paper
• Wetland Mapping Using Multi-Spectral Satellite Imagery and Deep Convolutional Neural Networks: A Case Study in Newfoundland and Labrador, Canada

  2021cited by this paper
• GPU-Accelerated CatBoost-Forest for Hyperspectral Image Classification Via Parallelized mRMR Ensemble Subspace Feature Selection

  2021cited by this paper
• Sentinel-1 SAR Backscatter Analysis Ready Data Preparation in Google Earth Engine

  2021cited by this paper
• A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme

  2021cited by this paper
• ESA WorldCover 10 m 2020 v100

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

  2021cited by this paper
• The Third Generation of Pan-Canadian Wetland Map at 10 m Resolution Using Multisource Earth Observation Data on Cloud Computing Platform

  2021cited by this paper
• Mapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data

  2020cited by this paper
• Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data: A case study in the St. Lucia wetlands, South Africa

  2020cited by this paper
• Scattering Feature Set Optimization and Polarimetric SAR Classification Using Object-Oriented RF-SFS Algorithm in Coastal Wetlands

  2020cited by this paper
• Deep learning Using Physically-Informed Input Data for Wetland Identification

  2020cited by this paper
• An Improved Power System Transient Stability Prediction Model Based on mRMR Feature Selection and WTA Ensemble Learning

  2020cited by this paper
• National wetland mapping in China: A new product resulting from object-based and hierarchical classification of Landsat 8 OLI images

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

  2020cited by this paper
• Meta-Analysis of Wetland Classification Using Remote Sensing: A Systematic Review of a 40-Year Trend in North America

  2020cited by this paper
• Mapping Coastal Wetlands of the Bohai Rim at a Spatial Resolution of 10 m Using Multiple Open-Access Satellite Data and Terrain Indices

  2020cited by this paper
• Meta-analysis of deep neural networks in remote sensing: A comparative study of mono-temporal classification to support vector machines

  2019cited by this paper
• A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing

  2019cited by this paper
• A new hybrid classifier selection model based on mRMR method and diversity measures

  2018cited by this paper
• Multi-temporal SAR image classification of coastal plain wetlands using a new feature selection method and random forests

  2018cited by this paper
• Enabling efficient, large-scale high-spatial resolution wetland mapping using satellites.

  2018cited by this paper
• A Parallelized Spark Based Version of mRMR

  2018cited by this paper
• Google Earth Engine: Planetary-scale geospatial analysis for everyone

  2017cited by this paper
• Maximum relevance, minimum redundancy band selection based on neighborhood rough set for hyperspectral data classification

  2016cited by this paper
• Plant Species Discrimination in a Tropical Wetland Using In Situ Hyperspectral Data

  2014cited by this paper
• SVM Land Cover Classification based on Spectral and Textural Features Using Stratified Samples

  2014cited by this paper
• Classification of cultivated Chinese medicinal plants based on fractal theory and gray level co-occurrence matrix textures

  2014cited by this paper
• Interactive Spectral Band Discovery for Exploratory Visual Analysis of Satellite Images

  2012cited by this paper
• A Research on Method of Wetland Vegetation Identification and Classification Based on Radar Backscatter Characteristics

  2012cited by this paper
• ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data

  2010cited by this paper
• Wetland monitoring using classification trees and SPOT-5 seasonal time series

  2010cited by this paper
• The Extraction of Freshwater Marsh Wetland Information Based on Decision Tree Algorithm——A Case Study in the Northeast of the Sanjiang Plain

  2008cited by this paper
• A review of feature selection techniques in bioinformatics

  2007cited by this paper
• Landscape biodiversity of wetlands and their changes in 50 years in watersheds of the Sanjiang Plain

  2004cited by this paper
• Feature selection for clustering - a filter solution

  2002cited by this paper

• Spartina alterniflora invasion-induced soil organic carbon content changes: An assessment by time-series remote sensing and machine learning

  2026cites this paper
• Detecting water in agricultural landscapes from remote sensing imagery: Methodological choices, sensor constraints and performance metrics

  2026cites this paper
• Spatio-temporal inversion of surface soil organic matter in the Hexi Corridor based on remote sensing data and multiple model integration

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

  2025cites this paper