AI-Driven Remote Sensing Techniques for Sustainable Groundwater Management along the East Coast of Andhra Pradesh and its Environmental Resilience
- DOI
- 10.2991/978-94-6239-606-7_12How to use a DOI?
- Keywords
- East Coast; Groundwater Management; Machine learning Algorithms; Remote Sensing; Saltwater Intrusion
- Abstract
The East Coast of Andhra Pradesh (ECAP) is characterized as a hydro-geologically critical and environmentally sensitive region that is struggling with significant, intensifying challenges. These include groundwater over-exploitation and saltwater intrusion (SWI), compounding threats that are further exacerbated by climate change impacts. Conventional monitoring techniques have historically proven insufficient, lacking the essential spatial and temporal resolution required for effective, proactive water resource management. This research addresses this crucial deficiency by developing and rigorously validating a novel, integrated framework that merges Artificial Intelligence (AI) with Remote Sensing (RS) data. The resultant methodology is specifically designed to support Sustainable Groundwater Management (SGM) and boost environmental resilience throughout the ECAP. Multi-source geospatial datasets were leveraged for this study, incorporating imagery from Lansdsat, interferometric synthetic aperture radar (Sentinel-1/InSAR), and gravity data from GRACE-FO. From these sources, crucial thematic indicators were derived, including land use/land cover, topographical metrics, ground subsidence, and anomalies in Terrestrial Water Storage. These indicators served as inputs to train and assess a suite of sophisticated machine learning algorithms (specifically Random Forest, XGBoost, and Deep Neural Networks). These models were applied to perform a dual-purpose predictive mapping exercise: (1) generating high-resolution maps of Groundwater Potential Zones (GWPZ), and (2) conducting a detailed SWI vulnerability assessment across critical coastal aquifers. The final predictions generated by these models were subsequently synthesized to produce a comprehensive Groundwater Resilience Index (GRI) map. This index uniquely integrates hydrological forecasts with established environmental stress indicators. The resulting high-fidelity predictive maps and the GRI constitute an actionable decision-support system. They provide direct, policy-relevant insights for implementing targeted, sustainable groundwater abstraction controls and informing crucial coastal environmental resilience planning in one of India’s most vulnerable geographic corridors.
- Copyright
- © 2026 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - M. R. Goutham AU - Suneel Kumar Duvvuri AU - Venkatesh Sunkara AU - G. Uma Mahesh AU - Srinivasa Rao Narra AU - K. Maneesha PY - 2026 DA - 2026/03/05 TI - AI-Driven Remote Sensing Techniques for Sustainable Groundwater Management along the East Coast of Andhra Pradesh and its Environmental Resilience BT - Proceedings of the International Conference on Resilient Innovations for Subsistence Environment (IC-RISE-2025) PB - Atlantis Press SP - 88 EP - 105 SN - 2468-5747 UR - https://doi.org/10.2991/978-94-6239-606-7_12 DO - 10.2991/978-94-6239-606-7_12 ID - Goutham2026 ER -