Researchers at the National Institute of Technology (NIT), Rourkela, have developed a machine learning-based model to evaluate groundwater quality. This innovation will help farmers determine whether the water they use for irrigation is suitable, ensuring better crop yield and soil fertility.
The research, conducted in Odisha's Sundargarh district, has been published in the Water Quality Research Journal. Agriculture is the primary economic activity in this region, but surface water sources cover only 1.21% of the total area. As a result, groundwater remains the main source of irrigation, making its quality crucial for farming.
As part of the study, water samples from 360 wells were analyzed for various chemical properties affecting soil and crop health. Using machine learning models and statistical tools, researchers found that groundwater in the southern, southwestern, and eastern parts of the district is suitable for irrigation. However, water quality in the western and central areas, including Krinjikela, Talsara, Kutra, and parts of Sundargarh town, showed concerning elements that could impact soil fertility and crop productivity.
Potential for Nationwide Implementation: The findings suggest that if water quality issues are not addressed, crops like potatoes and cucumbers may suffer a decline in yield. Additionally, researchers warn of a possible further decline in water quality in certain areas. Experts believe that the advanced model developed by NIT Rourkela can be utilized across India to assess groundwater quality, helping farmers improve irrigation management and agricultural productivity.
