Abstract:
Hangzhou possesses diverse and abundant wetland resources. With rapid urbanization, however, the total area of wetland has been shrinking. Issues such as degradation of ecosystem quality and functional decline have become increasingly severe. Consequently, it is crucial to conduct refined land cover classification of wetland types in Hangzhou, for effective wetland protection and management. In the present work, Google Earth Engine (GEE) cloud platform and Sentinel-2 satellite imagery data were used to categorize wetlands in Hangzhou with Random Forest Algorithm. A combination of multiple feature information substantially enhanced classification accuracy, compared to single-feature classification. Feature combination encompassed traditional spectral features, red-edge spectral features, transformed features, texture features, and topographic features, yielding an overall accuracy of 81.2% and a Kappa coefficient of 0.75. Different feature information contributed significantly to the extraction of various wetland types. Traditional spectral features were particularly advantageous for identifying tidal flats and aquaculture ponds. Red-edge spectral features and transformed features were more effective for recognizing herbaceous marshes and lakes respectively. Further, combining red-edge spectral features and texture features proved beneficial for identifying canals and water channels. The feature comparison experiment in this study is useful for future studies on refined wetland classification. The wetland classification results provide data support for remote sensing identification of wetland information in Hangzhou.