Characterization of forests is an important aspect for the management and conservation of biodiversity and satellite remote sensing provides opportunity to rapidly assess biodiversity patterns across large geographical areas. The present study aimed to characterize vegetation in a landscape with heterogenous topography using medium resolution Sentinel-2 satellite data and random forest (RF) machine learning algorithm. The study area falls in the Nandhaur landscape of western Himalayan foothills and forms an important part of the Terai Arc Landscape. Sentinel-2 satellite data of January, April and May months was used along with SRTM Digital Elevation Model. Primary field data was collected for dominant vegetation community characteristics and used for training and validation of the model in RF. A total of eleven forest vegetation communities was characterized with an accuracy of 70–87% for individual imageries as well as in collocation of images. Satellite image of April was found most useful for discriminating forest communities with high spectral separability among communities. Variable important analysis revealed Vegetation Red Edge, Narrow NIR and NIR bands were useful for discriminating communities with maximum information along with SWIR and Red bands. Study found that collocation of the multi-date images was useful for classifying communities with higher accuracies. This attempt at characterizing heterogeneous vegetation communities with advanced machine learning tools in Himalayan foothills showed encouraging outcomes which can be used in future studies for monitoring and management of key habitats in this area.

中文翻译：

---

使用 Sentinel-2 卫星数据和随机森林分类器在北阿坎德邦西部喜马拉雅山麓进行社区级植被表征

森林特征是生物多样性管理和保护的一个重要方面，卫星遥感为快速评估大地理区域的生物多样性模式提供了机会。本研究旨在使用中等分辨率 Sentinel-2 卫星数据和随机森林 (RF) 机器学习算法来表征具有异质地形的景观中的植被。研究区位于喜马拉雅西部山麓的Nandhaur景观中，是Terai Arc景观的重要组成部分。1 月、4 月和 5 月的 Sentinel-2 卫星数据与 SRTM 数字高程模型一起使用。收集了主要植被群落特征的主要实地数据，并用于在 RF 中训练和验证模型。总共有 11 个森林植被群落的特征在于单个图像以及图像搭配的准确度为 70-87%。发现 4 月的卫星图像对于区分群落之间具有高光谱可分离性的森林群落最有用。变量重要分析显示植被红边、窄 NIR 和 NIR 波段可用于区分具有最大信息以及 SWIR 和红波段的群落。研究发现，多日期图像的搭配有助于对更高准确度的社区进行分类。这种在喜马拉雅山麓用先进的机器学习工具表征异质植被群落的尝试显示出令人鼓舞的结果，可用于未来对该地区关键栖息地进行监测和管理的研究。