Related Experiment Video
Updated: Jul 16, 2026
06:37
Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds
Published on: November 13, 2017
Explainable artificial intelligence for groundwater quality prediction and hydrochemical interpretation.
G Shyamala1, Prakhash Neelamegam1, Belin Jude Alphonse2
1Department of Civil Engineering, School of Engineering, SR University, Warangal, 506371, Telangana, India.
Scientific Reports
|July 14, 2026
Summary
This study introduces an interpretable AI framework to predict groundwater quality, identifying key contaminants like ammonia, iron, and chromium. The approach enhances understanding for sustainable water resource management.
Area of Science:
- Environmental Science
- Data Science
- Hydrogeology
Background:
- Groundwater quality degradation is a growing concern due to urbanization, agriculture, and climate change.
- Accurate prediction and interpretation of groundwater quality are crucial for effective management.
- Existing methods often lack interpretability, hindering practical application.
Purpose of the Study:
- To develop an interpretable hybrid artificial intelligence (AI) framework for groundwater quality prediction and analysis.
- To integrate advanced machine learning algorithms with explainable AI (XAI) techniques.
- To identify dominant groundwater contaminants and understand influencing hydrogeochemical factors.
Main Methods:
- Collected 135 groundwater samples from Tamil Nadu, India, analyzing 16 physicochemical parameters.
- Applied data pre-processing techniques including cleaning, scaling, and outlier detection.
- Utilized stacked ensemble machine learning models (XGBoost, Random Forest, LightGBM, CatBoost) with Optuna hyperparameter tuning and XAI (SHAP, LIME).
Main Results:
- The stacked ensemble model achieved high predictive accuracy (R² = 0.938, RMSE = 0.237, MAE = 0.184).
- Water Quality Index analysis identified ammonia (NH₃), iron (Fe), and chromium (Cr) as primary contaminants.
- XAI methods revealed the buffering effects of ions like HCO₃⁻ and Ca²⁺ and indicated localized industrial pollution.
Conclusions:
- The proposed interpretable AI framework significantly improves groundwater quality prediction reliability.
- The study provides actionable insights into contaminant sources and hydrogeochemical processes.
- The framework supports sustainable groundwater management by offering both predictive accuracy and interpretability.
Related Concept Videos
01:14Testing Water Quality
When the quality of water for concrete preparation is uncertain, its impact on the setting time of cement and compressive strength of mortar is assessed by comparison with de-ionized or distilled water benchmarks. American Society for Testing and Materials (ASTM) C1602 requires the setting times to be within 90 minutes of the control, British Standard (BS) 3146:1980 allows a 30-minute variance in the initial setting, while British Standards European Norm (BS EN) 1008 specifies initial setting...
01:17Precipitation and Co-precipitation
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...