Optimization of land use and cover classification in the Samin watershed: An automated approach with Landsat-8 imagery and Google Earth Engine

Abstract Analyzing land use and land cover (LULC) is crucial for understanding community development and evaluating changes in the Anthropocene era. Traditional LULC mapping struggles with challenges like capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of LULC change descriptions, this study applies a blend of advanced techniques. Specifically, it utilizes Landsat-8 satellite imagery with a 30- meter multitemporal resolution, alongside the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, a random forest (RF) algorithm is integrated into the study. This research aims to generate sustainable LULC maps for the Samin Watershed for the years 2014 and 2023. A novel dual composite RF approach based on LULC classification is used to create the final LULC classification map, leveraging the RF-50 and RF-100 tree models. Both RF models use seven input bands (B1 to B7) as datasets for LULC classification.