Mapping of glacial lakes using Sentinel-1 and Sentinel-2 data and a random forest classifier: Strengths and challenges

The water body detection and mapping algorithm named 'glakemap' that I designed was aimed at specifically mapping glacial lakes across alpine regions where their detection and mapping are challenged by many factors such as shadows, cloud cover, turbidity, and ice surface. The algorithm uses Copernicus Sentinel-1 and -2 satellites data and machine learning model (random forest) in an integrated manner to automatically classify glacial lakes from other surface features. In specific, the algorithm takes Sentinel-1 and -2 satellites data as the main inputs. It calculates radar backscatter and Normalised Difference Water Indices (NDWIs) using these datasets, respectively. The radar backscatter and NDWIs products (images) are segmented using a set of rules producing many polygons including lake polygons. Lake polygons are then automatically separated/retained using the random forest model which is trained using features relevant to lakes. The dataset is also available at https://www.mountcryo.org/我设计的名为“glakemap”的水体检测与制图算法，旨在针对受阴影、云覆盖、浊度及冰面等多重因素制约，导致冰川湖泊检测与制图难度较高的高山区域，开展精准的冰川湖泊制图工作。该算法整合使用哥白尼（Copernicus）哨兵-1（Sentinel-1）与哨兵-2（Sentinel-2）卫星数据，并结合机器学习模型——随机森林（random forest），实现冰川湖泊与其他地表地物的自动化分类。具体而言，该算法以哨兵-1、2号卫星数据作为主要输入，分别基于上述数据集计算雷达后向散射系数与归一化差异水体指数（Normalised Difference Water Indices, NDWI）。随后，通过一系列规则对雷达后向散射系数与归一化差异水体指数产品（影像）进行影像分割，生成包含湖泊多边形在内的多个多边形要素。最后，利用以湖泊相关特征训练得到的随机森林模型，自动分离并保留湖泊多边形。本数据集可通过 https://www.mountcryo.org/ 获取。

搜集汇总

背景与挑战

背景概述

该数据集提供了一个名为'glakemap'的算法，用于自动检测和制图高山地区的冰川湖。它结合Sentinel-1和Sentinel-2卫星数据，通过计算雷达后向散射和归一化水体指数（NDWIs），并应用随机森林分类器来克服阴影、云覆盖等挑战。数据集覆盖喜马拉雅、阿尔卑斯和安第斯等区域，以支持冰川湖监测和研究。