This project presents a Machine Learning (ML)-based approach to assess the groundwater quality in the Nanjikottai region of Thanjavur, Tamil Nadu. Groundwater is a primary source for both domestic and agricultural needs in this area; however, increasing urbanization and agricultural runoff pose significant threats to its chemical integrity. Traditional water quality indexing methods often involve complex manual calculations and may struggle with large-scale, non-linear environmental data. To address this, we developed a predictive framework utilizing various ML algorithms to classify water samples based on key physicochemical parameters such as pH, Total Dissolved Solids (TDS), Electrical Conductivity (EC), Chlorides, and Nitrates.

EFFECTIVE ASSESSMENT: Successfully integrated Machine learning algorithms to assess groundwater quality in the Nanjikottai , Thanjavur region with high accuracy. WQI PREDICTION: The model effectively predicts the water quality index (WQI), reduction the needs for expensive and time – consuming manual laboratory testing. SPATIAL INSIGHTS: Identified critical zones of groundwater contamination, providing a clear map for local authorities to prioritize water treatment. DATA DRIVEN DECISIONS: Proved that AI/ML tools are essential for modern civil engineering projects in managing sustainable water resources. CUMMUNITY IMPACT: This research offers a scalable framework to ensure safe drinking water for the growing population in the Thanjavur districts.

[1]Real-Time loT Integration: Deploying low-cost sensors in Nanjikottai wells for live data streaming. Transitioning from static datasets toa Real-Time Water Quality Index (RWQI). [2]Spatio-Temporal Forecasting: Using LSTM (Long Short-Term Memory) networks to predict quality trends across different seasons in Thanjavur. Analyzing the long-term impact of agricultural runoff on groundwater. [3]Mobile Application Development: A user-friendly app for local residents to check potability based on their GPS location Real-Time loT Integration: Deploying low-cost sensors in Nanjikottai wells for live data streaming. Transitioning from static datasets toa Real-Time Water Quality Index (RWQI). [4]Spatio -Temporal Forecasting: Using LSTM (Long Short-Term Memory) networks to predict quality trends across different seasons in Thanjavur. Analyzing the long-term impact of agricultural runoff on groundwater. [5]Mobile Application Development: A user-friendly app for local residents to check potability based on their GPS location Rama Mohan, P., Neeli Mallikarjuna, A., & Niteesh Kumar, K. (2020). A Novel Over Voltage and Under Voltage Protecting System for Industrial and Domestic Applications. International Journal of Innovative Science and Research Technology, 5(10).

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close