35. Application of machine learning algorithms to assess land cover change - a case study in selected communes of Nghe An province

Abstract

Identifying changes in land use/land cover (LULC) is crucial for monitoring, assessing, and conserving natural resources. In several communes of Nghe An Province, the use of remote sensing data to evaluate the effectiveness of Machine Learning (ML) algorithms in LULC classification and change detection analysis remains limited. This study analyzes land cover dynamics in the study area from 2020 to 2024 using multi-temporal Landsat 8 imagery. The land cover classification results obtained using the Random Forest (RF) algorithm produced highly reliable land cover maps, as indicated by high Kappa coefficients (87.23 - 90.01 %).