Monitoring The Rate of Change of Vegetation Growth in Mine Rehabilitation Using Machine Learning

This study contributes to the literature on image processing, clustering, and time series forecasting in environmental monitoring. It successfully applied K-means clustering to segment HSV images, effectively tracking vegetation changes over time with high accuracy, despite challenges from lighting variations. The forecasting component, using Prophet, modelled vegetation growth in relation to mining activities through simulated scenarios, providing insights into the impact of external factors on vegetation. These findings enhance clustering techniques for image segmentation and offer a flexible method for monitoring and forecasting vegetation changes, with potential applications in ecological and environmental management.