Land use land cover change detection using multi-temporal Landsat imagery in the North of Congo Republic: a case study in Sangha region

Abstract

In recent years, satellite data have become available for free to the remote sensing community. Land use and land cover (LULC) changes are identified in remote sensing applications using Landsat satellite data. However, there is a lack of studies that utilize these data to assess the performance of satellite data on LULC classification and monitoring changes in complex landscapes. This study aims at evaluating LULC changes for the years 2013, 2018, and 2023 in the Sangha area using Landsat-8 OLI images. The Support Vector Machine (SVM) algorithm was implemented for detecting changes in the Sangha area. The results revealed that wetland forest and water bodies drastically declined, with a net change of −33.78 and-19.22%, respectively, while open forest, urban area, and bare soils with +77.91, +52.81, and +40.52% correspondingly substantially increased between 2013 and 2023. The overall accuracy and Kappa statistics achieved were above 91% and 0.85, respectively.

Keywords

• Land use and land cover
• change detection
• SVM classifier
• supervised classification
• Republic of Congo