<![CDATA[Unsupervised mining activities and the lack of proper management of the environment can bring very serious ecological effects. One of the worst is large-scale land cover change. This paper investigates the land cover changes in the mining area of PT Indonesia Weda Bay Industrial Park (IWIP), Weda Bay Nickel (WBN) area, and measures the performance of the Support Vector Machine technique of land cover classification using satellite imagery. This research is a quantitative study based on a remote sensing technique and spatial analysis in a GIS environment. Multi-temporal satellite images, Landsat-7 (2010), Landsat-8 (2014), and Sentinel-2 (2019 and 2025) were processed to land cover classes (vegetation, open land, cloud) based on the spectral indices NDVI, NDBI, and BSI. Through the post-classification comparison method, land cover changes were detected. The overall change from 2010 to 2025 is quite significant. The vegetation cover decreased from 91.2% to 84.3%, while open land increased from less than 1% to 11.4%. The greatest changes were observed in 2019 and 2025, suggesting that mining activities and related industry development have speed up A lot. The Support Vector Machine algorithm reached excellent classification accuracy over the different periods (97.47%, 96.67%, 89.52%, 95.12% in the cases of 2010 2014 2019 and 2025 respectively), and the results were supported by the high Kappa agreement scores (ranging from 0.84 to 0.96). The low difference between training and testing accuracy indicates a strong generalization without any sign of the model getting overfitted to the training data. The work highlights that Support Vector Machine algorithm, is a very good and reliable method for detecting land cover change in mining areas, where patterns are both complex as well as dynamic.]]>
