The global surge in demand for thermal power generation has driven rapid growth in coal mining, triggering landscape disturbances that inadvertently lead to vegetation loss, land degradation, ecosystem destabilization, habitat loss, climate anomalies, and an alarming threat to food security and livelihoods. Effective monitoring of coal mining sites and the extent of their expansion is essential to quantify the nature and scope of damage to native ecosystems, assess vulnerability, and develop strategies to prioritize future restoration efforts. Therefore, we investigated to evaluate the impact of coal mining on land cover destruction using Sentinel-2 data, employing machine learning (ML) algorithms and assessing degradation vulnerability through the Analytical Hierarchy Process (AHP) model. The findings reveal that the Support Vector Machine (SVM) outperformed the Random Forest (RF) and Gaussian Maximum Likelihood Classifier (MLC) algorithms, which were found to be suitable in characterizing land cover and vegetation. Over the past thirty years, coal mining has proliferated in forest and agricultural lands, leading to varying levels of degradation. AHP identified strong correlations among soil bulk density, organic carbon, the Normalized Difference Vegetation Index, and the Normalized Difference Moisture Index with degradation patterns; hence, these variables received higher weights in the analysis. The Land Degradation Vulnerability Index map, derived by integrating AHP variables within a Geographic Information System (GIS), illustrates the highest vulnerability in mined areas, followed by barren areas, agricultural lands, and forests. The study highlighted the effectiveness of the ML algorithm in precise land cover classification and the robustness of AHP techniques in analysing degradation. It further explores the implications of successful ecological restoration strategies that foster resilient ecosystems, aiming to reverse land degradation in coal-mined areas in alignment with the Sustainable Development Goals (SDGs) for 2030.