结果表明：1有效地使用多种特征变量是提高湿地信息提取的关键就不同特征对湿地信息提取的贡献率而言红边指数植被指数和水体指数光谱特征纹理特征；2基于随机森林算法优选的特征变量提取效果最佳总体精度高达8453Kappa系数为082表明随机森林算法可以有效地进行特征选择在特征变量数据挖掘的同时仍能保证湿地信息提取的精度提高运行效率。本研究为湿地信息提取在数据源选择、特征选择和方法选择方面提供了一种新思路、

The results indicate that: (1) effectively using multiple feature variables is key to improving wetland information extraction. In terms of the contribution of different features to wetland information extraction, the red edge index > vegetation index and water body index > spectral features > texture features; (2) the feature variable extraction based on the random forest algorithm has the best performance, with an overall accuracy of 84.53% and a Kappa coefficient of 0.82. This indicates that the random forest algorithm can effectively perform feature selection while ensuring the accuracy of wetland information extraction and improving operational efficiency. This study provides a new approach, method, and technical means for wetland information extraction in data source selection, feature selection, and method selection