ANALYSIS AND MAPPING OF LAND USE AND LANDCOVER (A CASE STUDY OF OYO STATE)

The purpose of this study is to assess the classification performance of the Maximum Likelihood-supervised strategy for land use/land cover (LULC) ARCGIS 10.3 classification methods. In order to comprehend environmental changes, urban planning, resource management, and sustainable development, land use and land cover (LULC) analysis and mapping are crucial. This study uses the maximum likelihood approach for supervised classification in order to classify LULC utilizing remote sensing techniques. To classify different types of land cover, including, builtup area, forest, baresoil, vegetation, water bodies, and rock, satellite images from LANDSAT 9/OLI/TIRS was processed and evaluated. Because of the maximum likelihood classification method's statistical rigor and capacity to manage a variety of land cover types, which improves accuracy of LULC mapping. For accurate classification, training samples were taken from validated ground truth data, and classification accuracy was evaluated using validation measures including the kappa coefficient and confusion matrix. Urban growth, deforestation, and other land cover changes were highlighted by the data, which also showed clear geographical patterns and temporal alterations in LULC. The effectiveness of supervised classification and maximum likelihood estimation for precise LULC mapping is demonstrated in this study, providing insightful information to environmental managers, urban planners, and policymakers for tracking land cover dynamics and promoting sustainable land management practices.