Classification of coastal wetlands in the Liaohe Delta with multi-source and multi-feature integration

Coastal wetlands, situated at the interface of land and sea, are the most productive ecosystems on the planet, boasting the richest biodiversity and the highest value in ecological services. The primary goal of this study is to analyze the spatial distribution of land use within the Liaohe Delta wetlands and to introduce a wetland classification system that integrates multiple sources and features, utilizing Google Earth Engine (GEE) for the Liaohe Delta wetlands. Firstly, the Sentinel 2 data were downloaded by median synthesis on GEE, after which random sample points were selected on QGIS, and secondly, the multi-source feature set was created by integrating data from Sentinel 1, Sentinel 2, and a Digital Elevation Model (DEM), utilizing the Recursive Feature Elimination (RFE) algorithm within a Random Forest (RF) framework to optimize feature selection. Various feature combination schemes were constructed to evaluate the impact of multi-source feature optimization on wetland classification performance. Ultimately, the Random Forest (RF) algorithm was employed to classify and extract wetlands in the study area. The findings indicate that the overall accuracy of the classification of the study area is 88.56%, and the Kappa coefficient is 0.8472. Compared with the results of using all the features for classification, the overall accuracy of the optimized features is improved by 3.83%, and the Kappa coefficient is improved by 0.0525. Compared with other machine learning methods, the overall accuracy and kappa of RF classification results improved by 1.06 to 22.77% and 0.0165 to 0.3248, respectively.