Abstract
The rapid groundwater depletion and the deterioration in groundwater quality in the major aquifers around the globe due to anthropogenic stress and natural causes have raised serious concerns over the usable groundwater resources worldwide. While the rapid depletion is attributed to pervasive groundwater abstraction for agriculture, industrial, and domestic use, contamination from various natural and human-induced origins are primary contributors in the deterioration of groundwater quality. Thus a smart, efficient local to regional scale framework for sustainable groundwater management based on informed modeling approaches and verifiable data is required. In recent years, data-driven methods such as artificial intelligence (AI) methods are reported to be better suited modeling approaches than numerical, conceptual, and physically based methods in the field of hydrology. Hence, these black-box tools can be effectively employed to model groundwater quantity and distribution of major contaminants in groundwater. Using proper modeling techniques, incorporating the knowledge and data on the dependent and other independent variables may lead to a better understanding on the primary triggers changing the groundwater dynamics and the factors influencing the distribution of contaminants in groundwater in the present and the future. Considering the greater data availability in recent times, these methods would be able to produce more accurate predictions and can be useful in better management of groundwater resources. Here, in this chapter, we provide a brief overview based on previous literature followed by some of the case studies on groundwater modeling using AI in India.
Original language | English |
---|---|
Title of host publication | Global Groundwater |
Subtitle of host publication | Source, Scarcity, Sustainability, Security, and Solutions |
Publisher | Elsevier |
Pages | 545-557 |
Number of pages | 13 |
ISBN (Electronic) | 9780128181720 |
DOIs | |
State | Published - Jan 1 2020 |
Externally published | Yes |
Keywords
- Artificial intelligence (AI)
- Deep learning (DL)
- Groundwater prediction
- Groundwater quality
- Groundwater quantity
- Machine learning (ML)