Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Integrating Boosted learning with Differential Evolution (DE) Optimizer: A Prediction of Groundwater Quality Risk Assessment in Odisha

Sonalika Subudhi, Alok Kumar Pati, Sephali Bose, Subhasmita Sahoo, Avipsa Pattanaik, Biswa Mohan Acharya

TL;DR

This work tackles groundwater quality risk in Odisha, focusing on heavy-metal contamination and the Groundwater Quality Index (GWQI). It introduces LCBoost Fusion, a hybrid of LightGBM and CatBoost whose weights are optimized by Differential Evolution, to predict GWQI with high accuracy. Using CGWB data from 2019–2022, the approach achieves state-of-the-art performance (RMSE 0.6829, MSE 0.5102, MAE 0.3147, $R^2 = 0.9809$) and identifies Potassium, Fluoride, and Total Hardness as key predictors. The study provides a data-driven tool for real-time groundwater monitoring and targeted management in Odisha, with potential extension to remote sensing data and broader pollutant sets to support policy and public health decisions.

Abstract

Groundwater is eventually undermined by human exercises, such as fast industrialization, urbanization, over-extraction, and contamination from agrarian and urban sources. From among the different contaminants, the presence of heavy metals like cadmium (Cd), chromium (Cr), arsenic (As), and lead (Pb) proves to have serious dangers when present in huge concentrations in groundwater. Long-term usage of these poisonous components may lead to neurological disorders, kidney failure and different sorts of cancer. To address these issues, this study developed a machine learning-based predictive model to evaluate the Groundwater Quality Index (GWQI) and identify the main contaminants which are affecting the water quality. It has been achieved with the help of a hybrid machine learning model i.e. LCBoost Fusion . The model has undergone several processes like data preprocessing, hyperparameter tuning using Differential Evolution (DE) optimization, and evaluation through cross-validation. The LCBoost Fusion model outperforms individual models (CatBoost and LightGBM), by achieving low RMSE (0.6829), MSE (0.5102), MAE (0.3147) and a high R$^2$ score of 0.9809. Feature importance analysis highlights Potassium (K), Fluoride (F) and Total Hardness (TH) as the most influential indicators of groundwater contamination. This research successfully demonstrates the application of machine learning in assessing groundwater quality risks in Odisha. The proposed LCBoost Fusion model offers a reliable and efficient approach for real-time groundwater monitoring and risk mitigation. These findings will help the environmental organizations and the policy makers to map out targeted places for sustainable groundwater management. Future work will focus on using remote sensing data and developing an interactive decision-making system for groundwater quality assessment.

Integrating Boosted learning with Differential Evolution (DE) Optimizer: A Prediction of Groundwater Quality Risk Assessment in Odisha

TL;DR

This work tackles groundwater quality risk in Odisha, focusing on heavy-metal contamination and the Groundwater Quality Index (GWQI). It introduces LCBoost Fusion, a hybrid of LightGBM and CatBoost whose weights are optimized by Differential Evolution, to predict GWQI with high accuracy. Using CGWB data from 2019–2022, the approach achieves state-of-the-art performance (RMSE 0.6829, MSE 0.5102, MAE 0.3147, ) and identifies Potassium, Fluoride, and Total Hardness as key predictors. The study provides a data-driven tool for real-time groundwater monitoring and targeted management in Odisha, with potential extension to remote sensing data and broader pollutant sets to support policy and public health decisions.

Abstract

Groundwater is eventually undermined by human exercises, such as fast industrialization, urbanization, over-extraction, and contamination from agrarian and urban sources. From among the different contaminants, the presence of heavy metals like cadmium (Cd), chromium (Cr), arsenic (As), and lead (Pb) proves to have serious dangers when present in huge concentrations in groundwater. Long-term usage of these poisonous components may lead to neurological disorders, kidney failure and different sorts of cancer. To address these issues, this study developed a machine learning-based predictive model to evaluate the Groundwater Quality Index (GWQI) and identify the main contaminants which are affecting the water quality. It has been achieved with the help of a hybrid machine learning model i.e. LCBoost Fusion . The model has undergone several processes like data preprocessing, hyperparameter tuning using Differential Evolution (DE) optimization, and evaluation through cross-validation. The LCBoost Fusion model outperforms individual models (CatBoost and LightGBM), by achieving low RMSE (0.6829), MSE (0.5102), MAE (0.3147) and a high R score of 0.9809. Feature importance analysis highlights Potassium (K), Fluoride (F) and Total Hardness (TH) as the most influential indicators of groundwater contamination. This research successfully demonstrates the application of machine learning in assessing groundwater quality risks in Odisha. The proposed LCBoost Fusion model offers a reliable and efficient approach for real-time groundwater monitoring and risk mitigation. These findings will help the environmental organizations and the policy makers to map out targeted places for sustainable groundwater management. Future work will focus on using remote sensing data and developing an interactive decision-making system for groundwater quality assessment.

Paper Structure

This paper contains 30 sections, 20 equations, 8 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Materials and Methodology
  3. Study Area
  4. Data Collection and Data Description
  5. Calculating Ground Water Quality Index (GWQI) score
  6. Selecting the required Water Quality Indicators (WQI)
  7. Calculating Sub-Index (SI)
  8. GWQI Score Aggregation function
  9. Procedure for GWQI prediction
  10. Data pre-processing
  11. Data Cleaning
  12. Feature Engineering
  13. Data Standardization
  14. Data splitting
  15. Machine Learning Algorithms
  16. ...and 15 more sections

Figures (8)

  • Figure 1: Location Map: Country Map showing the national context of the study area, State Map showing the regional location within the country, District Map demonstrating the area where the Sukinda Valley is located.
  • Figure 2: Workflow Diagram.
  • Figure 3: Feature Correlation Matrix.
  • Figure 4: Box Plot of Features for Outlier Detection.
  • Figure 5: Boxplots of features before and after Outlier Removal
  • ...and 3 more figures