Integrated Analysis of Land Subsidence in the Raniganj Coal Mining Region, India Using Multi-Source Earth Observation and AI-Enhanced Techniques

Raniganj, India is a well-known coal mining region characterized by high coal productivity and ongoing land subsidence. Land subsidence can be due to various factors such as mining activities, coal fire, total water storage change, atmospheric loading, oceanic loading, groundwater over-extraction, etc., but mining activities in the region are accredited to be one of the major sources of land subsidence. Despite its complex hydrological environment, where significant contributions arise from surface and subsurface water systems linked to the Ganges River system and proximity to the Bay of Bengal, non-mining factors' role in regional deformation patterns has not been thoroughly investigated. This study attempts to identify the potential sources of the ongoing subsidence in the region using various Earth Observation and Global Positioning Station (GPS) datasets. The deformation pattern of the area was analyzed using ground-based GPS measurements and the interferometric SAR (InSAR) technique with Sentinel-1 Synthetic Aperture Radar data. Seasonal variations in deformation, including pre-monsoon, co-monsoon, and post-monsoon periods, were assessed using total water storage (TWS) changes from the Gravity Recovery and Climate Experiment (GRACE) and Global Land Data Assimilation System (GLDAS) datasets. However, GRACE's coarser resolution and data gaps posed challenges for finer-scale interpretation. To address this, high-resolution datasets such as precipitation, Normalized Difference Vegetation Index (NDVI), and land surface temperature data were utilized in conjunction with Artificial Intelligence (AI) and Machine Learning (ML) techniques to downscale GRACE-derived TWS data, enabling higher-resolution insights into groundwater variability. This comprehensive approach provides a deeper understanding of the causative factors of land deformation in the region, especially the interactions between groundwater changes and other environmental variables. Such insights are crucial for informed land use and planning in this economically and environmentally sensitive region.