EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ensemble Machine Learning for Reliable Water Potability Prediction with Optimized Physicochemical Feature Engineering

Rohit Srivastava, Keshav Sinha, Dheeraj Samanta, Reham Alsabet, Walid El-Shafai, Ahmad Taher Azar

Engineering, Technology & Applied Science Research · 04.04.2026 · 16 (2) · 33647-33659

DOI: 10.48084/etasr.16495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 04.04.2026. Verfasst von Rohit Srivastava und 5 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Access to safe drinking water is a global challenge for both health and sustainability. This study presents a comprehensive examination of supervised machine learning models for water potability classification using physicochemical water quality characteristics, and a leakage-safe preprocessing pipeline incorporating stratified data splitting, mean imputation, and feature standardization. Class imbalance is handled by the Synthetic Minority Over-Sampling Technique (SMOTE), and feature selection and normalization were used to preprocess the dataset. Grid search and 5-fold cross-validation were used to train and optimize models, namely Random Forest (RFC), Logistic Regression (LR), Decision Tree (DTC), AdaBoost, K-Nearest Neighbor (KNN), Support Vector Classifier (SVC), and Gradient Boosting (GBC). Accuracy, precision, recall, and F1 score on the test set were used to assess performance, showing that ensemble approaches, namely RFC and GBC, performed better, having outstanding stability and prediction accuracy. Preprocessing contributes to increasing model sensitivity to the minority class, while balancing trade-offs between interpretability and model complexity are discussed. The findings contribute to the development of reliable, data-driven water quality monitoring systems that can align with sustainable development and public health goals. Since the limited dataset size may affect the generalizability to other regions, future studies should validate these findings on more diverse and comprehensive datasets.

Zitieren

APA

Srivastava, R., Sinha, K., Samanta, D., Alsabet, R., El-Shafai, W., & Azar, A. T. (2026). Ensemble Machine Learning for Reliable Water Potability Prediction with Optimized Physicochemical Feature Engineering. Engineering, Technology & Applied Science Research, 16(2), 33647-33659. https://doi.org/10.48084/etasr.16495

Vancouver

Srivastava R, Sinha K, Samanta D, Alsabet R, El-Shafai W, Azar AT. Ensemble Machine Learning for Reliable Water Potability Prediction with Optimized Physicochemical Feature Engineering. Engineering, Technology & Applied Science Research. 2026;16(2):33647-33659. doi:10.48084/etasr.16495

BibTeX
@article{Srivastava2026,
  author = {Srivastava, Rohit and Sinha, Keshav and Samanta, Dheeraj and Alsabet, Reham and El-Shafai, Walid and Azar, Ahmad Taher},
  title = {Ensemble Machine Learning for Reliable Water Potability Prediction with Optimized Physicochemical Feature Engineering},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {33647--33659},
  doi = {10.48084/etasr.16495}
}
Kostenlos starten →