Pious et al. (2026) Spatial-temporal variability and risk assessment of surface and groundwater resources under climate change and urbanization: A physics-informed analysis

Identification

• Journal: The Science of The Total Environment
• Year: 2026
• Date: 2026-04-01
• Authors: K. Joseph Pious, A. Stanley Raj
• DOI: 10.1016/j.scitotenv.2026.181723

Research Groups

Department of Physics, Loyola College, Chennai, Tamil Nadu, India.

Short Summary

This study developed a Physics-Informed Neural Network (PINN) framework to simulate groundwater dynamics and assess groundwater stress risk in the Chennai metropolitan region, India, revealing that 34% of the area faces high-to-critical stress, largely driven by climate and land-use changes.

Objective

• To develop a Physics-Informed Neural Network (PINN) framework to simulate groundwater dynamics and quantify groundwater stress risk in the Chennai metropolitan region, India, under the combined effects of climate variability and land-use change.

Study Configuration

• Spatial Scale: Chennai metropolitan region, India.
• Temporal Scale: Two decades (2000–2020).

Methodology and Data

• Models used: Physics-Informed Neural Network (PINN) for groundwater dynamics simulation and risk assessment; MODFLOW for benchmarking. A fuzzy multi-criteria risk framework was used for stress classification.
• Data sources: Observations from 347 monitoring wells (2000–2020), integrating recharge, pumping, and hydrogeological parameters. Independent field-based groundwater status assessments for validation.

Main Results

• The PINN model accurately simulates groundwater dynamics, performing robustly when benchmarked against MODFLOW and demonstrating spatial transferability.
• Climate variability and land-use intensity jointly explain approximately 61% of the observed spatial variability in groundwater decline rates.
• A bivariate demand-availability framework identified 34% of the Chennai region as currently falling within high-to-critical groundwater stress zones.
• The fuzzy multi-criteria risk framework achieved 91.4% overall accuracy in classifying groundwater stress.
• Over two decades (2000-2020), groundwater recharge declined by 18% while water demand increased by 32%, intensifying stress in hard-rock areas.

Contributions

• Development and validation of a novel Physics-Informed Neural Network (PINN) framework for robust spatial-temporal groundwater dynamics simulation and risk assessment.
• Quantification of the relative contributions of climate variability and land-use change to groundwater decline rates.
• Creation of a highly accurate fuzzy multi-criteria risk framework for classifying groundwater stress.
• Generation of predictive risk layers to guide block-level groundwater recharge policy interventions in rapidly urbanizing coastal regions.

Funding

Not specified in the provided text.

Citation

@article{Pious2026Spatialtemporal,
  author = {Pious, K. Joseph and Raj, A. Stanley},
  title = {Spatial-temporal variability and risk assessment of surface and groundwater resources under climate change and urbanization: A physics-informed analysis},
  journal = {The Science of The Total Environment},
  year = {2026},
  doi = {10.1016/j.scitotenv.2026.181723},
  url = {https://doi.org/10.1016/j.scitotenv.2026.181723}
}