Land Use Land Cover Classification Using Machine Learning and Remote Sensing Data: A Case Study of Karnaprayag, Uttarakhand, India

Land use and land cover (LULC) classification is crucial for planning and sustainable development, especially in mountainous regions. This study focuses on the Tehsil Karnaprayag, situated in the vicinity of the Greater Himalaya. With a total area of 1858.903 km<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and elevations ranging from 647m to 7641m. Using multispectral Sentinel-2 imagery and Machine Learning techniques i.e. Extreme gradient boosting (XGBoost) and K-nearest neighbor (KNN). This study aims to classify seven distinct land cover classes: snow, forest, water bodies, grassland, agricultural land, fallow land, and built-up areas. The classification results demonstrate the effectiveness of XGBoost classifier achieving an accuracy of 90.22% and a kappa value of 0.882, while KNN achieved an accuracy of 88.59% with a kappa value of 0.862. The analysis reveals that forest and fallow land are the predominant land cover types in the study area, constituting nearly 60% and 15% of the total area respectively. Notably, XGBoost exhibits the highest class-specific accuracy of 97.60<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> for the snow class, demonstrating its utility in discriminating between challenging land cover types. This research highlights the importance of LULC classification in informing land management strategies and facilitating sustainable development initiatives in mountainous regions. The findings provide valuable insights into the spatial distribution and composition of land cover in Tehsil Karnaprayag, essential for effective planning and conservation efforts in the Himalayan ecosystem.