AI to detect risk of groundwater arsenic exposure
doi:10.1038/nindia.2020.147 Published online 24 September 2020
Researchers from the Indian Institute of Technology in Kharagpur have developed specific models to assess the risks of groundwater arsenic exposure within the Ganges river delta, across parts of eastern India and south-western Bangladesh1.
These models, they say, are also essential for evaluating the health of arsenic-exposed people in the delta region.
Previous models, designed to assess the arsenic pollution in the same region, did not incorporate environmental factors such as subsurface hydrogeological systems. To overcome this drawback, the IIT scientists, led by Abhijit Mukherjee, devised several models by combining statistical methods with artificial intelligence techniques.
Using these models that include various environmental factors, they assessed groundwater arsenic hazard in 25 districts of India and Bangladesh with a total population of almost 110 million people. The models allowed them to create a digital map that shows that half of the regions in the Ganges river delta are vulnerable to elevated arsenic exposure.
The worst-affected districts from the state of West Bengal in India are Nadia and Murshidabad. A total of 30.3 million people are estimated to be exposed to severely high arsenic levels within the Ganges river delta.
They found groundwater-fed irrigation to be the strongest factor in causing arsenic hazard.
This study, the researchers say, forms the baseline knowledge for the recently launched state-run Jal Jeevan Mission, designed to provide safe drinking water to every Indian family by 2024.
1. Chakraborty, M. et al. Modeling regional-scale groundwater arsenic hazard in the transboundary Ganges River Delta, India and Bangladesh: Infusing physically-based model with machine learning. Sci. Total. Environ. 748, 141107 (2020)