 This paper proposes a novel methodology for identifying wetlands using remote sensing data. It combines the advantages of multiple sensors and data sources to improve the accuracy of wetland identification. The authors used a random forest algorithm to combine the data from different sensors and data sources, including PLEAD, 1B imagery, Landsat, A and DVI time series, and geometric and spectral features. The resultant classification accuracy was found to be higher than other classifiers, such as support vector machines and artificial neural networks. Additionally, the inclusion of phenological information in the classification enabled the classification errors to be reduced, resulting in an overall accuracy improvement of approximately 10%. This article was authored by Xiaohong Tian, Sianfeng Zhang, Jia Tian, and others.