Kumar et al. (2026) Interferometric synthetic aperture radar-artificial intelligence-based approach for groundwater level prediction in arid regions

Identification

• Journal: Elsevier eBooks
• Year: 2026
• Date: 2026-01-01
• Authors: Narendra Kumar, Anurag Aeron, Madhusudan Narayan
• DOI: 10.1016/b978-0-443-36394-8.00004-2

Research Groups

• Department of CSE, Amity University Jharkhand, Ranchi, Jharkhand, India
• Meerut Institute of Engineering & Technology (MIET), Meerut, Uttar Pradesh, India

Short Summary

This paper proposes an integrated Interferometric Synthetic Aperture Radar (InSAR) and Artificial Intelligence (AI) approach to accurately predict groundwater levels in arid regions by detecting millimeter-scale surface deformations. This novel methodology aims to overcome the limitations of traditional methods, offering unparalleled precision for sustainable groundwater management.

Objective

• To develop and apply an integrated InSAR-Artificial Intelligence approach for accurate and precise groundwater level prediction in arid and semi-arid regions, addressing the shortcomings of traditional, data-sparse methods.

Study Configuration

• Spatial Scale: Arid and semi-arid regions, with a specific example from California's San Joaquin Valley. The approach leverages satellite-based remote sensing, implying broad geographical applicability.
• Temporal Scale: Continuous monitoring capability for surface deformation over time, detecting minute changes (millimeter-scale) and annual rates of subsidence (e.g., up to 0.6 meters per year).

Methodology and Data

• Models used: Artificial Intelligence (AI) and Machine Learning (ML) algorithms.
• Data sources: InSAR measurements (e.g., from Sentinel-1 satellite mission's C-band synthetic aperture radar), satellite imagery, and climate data.

Main Results

• The integrated InSAR-AI approach effectively detects millimeter-scale surface deformations directly linked to subsurface groundwater level changes.
• This methodology enables the creation of accurate and trustworthy forecasting models for groundwater levels with unparalleled precision.
• Satellite-derived InSAR data has demonstrated significant land subsidence, such as up to 0.6 meters per year in California’s San Joaquin Valley, directly attributable to excessive groundwater extraction.

Contributions

• Introduces a novel integration of InSAR technology with Artificial Intelligence and Machine Learning algorithms for highly precise groundwater level prediction.
• Overcomes limitations of traditional groundwater prediction methods by utilizing remote sensing data to capture complex subsurface dynamics.
• Provides the capability to detect minute (millimeter-scale) surface deformations, offering unprecedented insights into groundwater depletion and recharge.
• Offers a sophisticated tool for sustainable groundwater management, particularly crucial for water-scarce arid and semi-arid regions.

Funding

• Not specified in the provided text.

Citation

@article{Kumar2026Interferometric,
  author = {Kumar, Narendra and Aeron, Anurag and Narayan, Madhusudan},
  title = {Interferometric synthetic aperture radar-artificial intelligence-based approach for groundwater level prediction in arid regions},
  journal = {Elsevier eBooks},
  year = {2026},
  doi = {10.1016/b978-0-443-36394-8.00004-2},
  url = {https://doi.org/10.1016/b978-0-443-36394-8.00004-2}
}