From data to decision: leveraging machine learning and water quality index for groundwater quality evaluation
Bibliographic record
Abstract
Groundwater quality is critical for sustainable development, serving as a primary source of drinking water and irrigation. The present study employs the machine learning (ML) models to evaluate the water quality index (WQI) in order to enhance the groundwater quality assessment. Forty groundwater samples were collected from six diverse locations and analyzed for seven physicochemical parameters, including pH, Turbidity, CO₂, Chloride, Alkalinity, TDS, and Fe. To improve model generalizability, data augmentation techniques, Gaussian noise and interpolation, expanded the dataset to 120 samples. WQI was computed using the Canadian Council of Ministers of the Environment (CCME) method. Six ML models were employed for predictive analysis and evaluated based on R2, RMSE, and MAE. The results revealed significant contamination, with 25% of samples exceeding acceptable limits for total dissolved solids (TDS), while iron levels averaged 3.01 mg/L, ten times higher than the WHO guideline of 0.3 mg/L. WQI values ranged from 45.89 to 100, classifying most samples as "Fair to Good" but identifying critical degradation in specific areas. Among the six ML models tested, XG-Boost outperformed the others, achieving the highest predictive accuracy (R2 = 0.97, RMSE = 1.72, MAE = 1.38). These findings highlight substantial groundwater contamination risks, particularly from iron and turbidity. This research demonstrates the effectiveness of ML in groundwater quality assessment, providing a scalable decision-support framework for environmental management and policymaking in resource-limited regions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".