Large-scale Internet of Things deployment for water quality monitoring systems is bounded by the capital and several other costs associated with the multi-dimensional sensor. While prior research demonstrates strong predictive performance using multi- parameter physicochemical sensing, limited attention has been given to explicit sensing cost constraints and deployment feasibility. This work formulates multiclass water quality classification as a cost-constrained learning problem in which sensing dimensionality is minimized subject to bounded degradation in predictive performance. A leakage-aware and imbalance-sensitive pipeline is developed using XGBoost with SMOTE-based training. The selected deployment model achieves an F1-score of about 0.9413and a significant Macro ROC-AUC : 0.9924 on unseen test data, demonstrating strong discriminative capability across five water quality categories. A secondary deployment-oriented experiment evaluates sensor minimization under cost constraints. A reduced three-parameter configuration (NO3, pH, EC) achieves a Weighted F1-score of 0.8737, retaining 89.5% of the optimized nine-sensor configuration performance while reducing sensing dimensionality by 66.7%. Multi-level testing with Monte Carlo, incorporating edge level feasibility tests, compatibility test with resource constraints. Integrating the combined support for robustness and sensing cost. The paper implements into the objective of learning designs and deployment aware of scalable and cost-effective IoT based environmental water quality monitoring systems.

Keywords- Water quality monitoring, Internet of Things, sensor reduction, constrained optimization, gradient boosting, edge intelligence, class imbalance, robustness analysis.

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Chen T, Guestrin C. Xgboost: A scalable tree boosting system. InProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 785-794).
2. McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA. Communication- efficient learning of deep networks from decentralized data. InArtificial intelligence and statistics 2017 Apr 10 (pp. 1273-1282). Pmlr.
3. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in neural information processing systems. 2017;30.
4. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research. 2002 Jun 1;16:321-57.
5. Breiman L. Random forests. Machine learning. 2001 Oct;45(1):5-32.
6. World Health Organization. Guidelines for drinking-water quality: first addendum to the fourth edition.
7. Sameer HA, Alkhafaj RM, Najim MA, Anssar OM. Internet of Things and Artificial Intelligence-Based Sensing Systems for Environmental Monitoring and Risk Assessment: A Systematic Review. Journal of Iraqi Al-Khawarizmi. 2026 Jun 6;10(1):137-59.
8. Lal K, Menon S, Noble F, Arif KM. Low-cost IoT based system for lake water quality monitoring. Plos one. 2024 Mar 28;19(3):e0299089.
9. Huang Y, Wang C, Wang Y, Lyu G, Lin S, Liu W, Niu H, Hu Q. Application of machine learning models in groundwater quality assessment and prediction: progress and challenges. Frontiers of Environmental Science & Engineering. 2024 Mar;18(3):29.
10. Guyon I, Elisseeff A. An introduction to variable and feature selection. Journal of machine learning research. 2003;3(Mar):1157-82.
11. He H, Garcia EA. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering. 2009 Jun 26;21(9):1263-84.
12. Kullback S, Leibler RA. On information and sufficiency. The annals of mathematical statistics. 1951 Mar 1;22(1):79-86.
13. Lee BM, Yang H. Energy-efficient massive MIMO in massive industrial Internet of Things networks. IEEE Internet of Things Journal. 2021 Jul 19;9(5):3657-71.
14. Saravanan K, Anusuya E, Kumar R, Son LH. Real-time water quality monitoring using Internet of Things in SCADA. Environmental monitoring and assessment. 2018 Sep;190(9):556.
15. Horton RK. An index number system for rating water quality. J Water Pollut Control Fed. 1965 Mar;37(3):300-6.

Large-scale Internet of Things deployment for water quality monitoring systems is bounded by the capital and several other costs associated with the multi-dimensional sensor. While prior research demonstrates strong predictive performance using multi- parameter physicochemical sensing, limited attention has been given to explicit sensing cost constraints and deployment feasibility. This work formulates multiclass water quality classification as a cost-constrained learning problem in which sensing dimensionality is minimized subject to bounded degradation in predictive performance. A leakage-aware and imbalance-sensitive pipeline is developed using XGBoost with SMOTE-based training. The selected deployment model achieves an F1-score of about 0.9413and a significant Macro ROC-AUC : 0.9924 on unseen test data, demonstrating strong discriminative capability across five water quality categories. A secondary deployment-oriented experiment evaluates sensor minimization under cost constraints. A reduced three-parameter configuration (NO3, pH, EC) achieves a Weighted F1-score of 0.8737, retaining 89.5% of the optimized nine-sensor configuration performance while reducing sensing dimensionality by 66.7%. Multi-level testing with Monte Carlo, incorporating edge level feasibility tests, compatibility test with resource constraints. Integrating the combined support for robustness and sensing cost. The paper implements into the objective of learning designs and deployment aware of scalable and cost-effective IoT based environmental water quality monitoring systems.

Keywords- Water quality monitoring, Internet of Things, sensor reduction, constrained optimization, gradient boosting, edge intelligence, class imbalance, robustness analysis.

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Chen T, Guestrin C. Xgboost: A scalable tree boosting system. InProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 785-794).
2. McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA. Communication- efficient learning of deep networks from decentralized data. InArtificial intelligence and statistics 2017 Apr 10 (pp. 1273-1282). Pmlr.
3. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in neural information processing systems. 2017;30.
4. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research. 2002 Jun 1;16:321-57.
5. Breiman L. Random forests. Machine learning. 2001 Oct;45(1):5-32.
6. World Health Organization. Guidelines for drinking-water quality: first addendum to the fourth edition.
7. Sameer HA, Alkhafaj RM, Najim MA, Anssar OM. Internet of Things and Artificial Intelligence-Based Sensing Systems for Environmental Monitoring and Risk Assessment: A Systematic Review. Journal of Iraqi Al-Khawarizmi. 2026 Jun 6;10(1):137-59.
8. Lal K, Menon S, Noble F, Arif KM. Low-cost IoT based system for lake water quality monitoring. Plos one. 2024 Mar 28;19(3):e0299089.
9. Huang Y, Wang C, Wang Y, Lyu G, Lin S, Liu W, Niu H, Hu Q. Application of machine learning models in groundwater quality assessment and prediction: progress and challenges. Frontiers of Environmental Science & Engineering. 2024 Mar;18(3):29.
10. Guyon I, Elisseeff A. An introduction to variable and feature selection. Journal of machine learning research. 2003;3(Mar):1157-82.
11. He H, Garcia EA. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering. 2009 Jun 26;21(9):1263-84.
12. Kullback S, Leibler RA. On information and sufficiency. The annals of mathematical statistics. 1951 Mar 1;22(1):79-86.
13. Lee BM, Yang H. Energy-efficient massive MIMO in massive industrial Internet of Things networks. IEEE Internet of Things Journal. 2021 Jul 19;9(5):3657-71.
14. Saravanan K, Anusuya E, Kumar R, Son LH. Real-time water quality monitoring using Internet of Things in SCADA. Environmental monitoring and assessment. 2018 Sep;190(9):556.
15. Horton RK. An index number system for rating water quality. J Water Pollut Control Fed. 1965 Mar;37(3):300-6.