Predicting water quality using deep learning techniques

Subject Areas : watere sciences

Mohammad Mehrani ¹

1 -

Received: 2025-02-15 Accepted : 2025-03-04 Published : 2024-09-19

Keywords: Water quality prediction, random forest, XGBoost, pH, dissolved oxygen, nitrate, phosphate,

Abstract :

Water quality prediction is one of the important issues in water resources management and environment. In this paper, two powerful machine learning algorithms, namely Random Forest and XGBoost, are used to predict water quality parameters. The inputs of the model include four main water quality characteristics, namely Temperature, Turbidity, Chlorophyll, and Conductivity. The outputs of the model also include four key water quality parameters, namely pH, Dissolved Oxygen (DO), Nitrate, and Phosphate. After data preprocessing, the Random Forest and XGBoost models were trained by adjusting appropriate hyperparameters. The performance of the models was evaluated using evaluation criteria including Mean Square Error (MSE), Root Mean Square Error (RMSE), and Coefficient of Determination (R²). The results showed that both models were able to predict water quality parameters with very high accuracy (about 99%). The comparative plots of actual and predicted values ​​for each output, along with the R² values, clearly demonstrate the excellent performance of the models. Also, the feature importance analysis showed that all four input features play an important role in predicting water quality parameters. This study demonstrates that the use of Random Forest and XGBoost algorithms can be used as an effective and accurate method for predicting water quality in water resource management systems.

References:

1. Chapman, D. (1996). Water Quality Assessments: A Guide to the Use of Biota, Sediments and Water in Environmental Monitoring. UNESCO/WHO/UNEP.
2. Heddam, S., Kisi, O., & Sebbar, A. (2020). Machine Learning Approaches for Predicting Water Quality Parameters: A Comprehensive Review. Environmental Modelling & Software, 124, 104631.
3. Najah, A., El-Shafie, A., Karim, O. A., & El-Shafie, A. H. (2013). Application of Artificial Neural Networks for Water Quality Prediction. Neural Computing and Applications, 22(1), 187-201.
4. FAO. (2020). The State of the World’s Land and Water Resources for Food and Agriculture. Food and Agriculture Organization of the United Nations.
5. IPCC. (2021). Climate Change 2021: The Physical Science Basis. Intergovernmental Panel on Climate Change.
6. Smith, V. H., Tilman, G. D., & Nekola, J. C. (1999). Eutrophication: Impacts of Excess Nutrient Inputs on Freshwater, Marine, and Terrestrial Ecosystems. Environmental Pollution, 100(1-3), 179-196.
7. UN Water. (2021). The United Nations World Water Development Report 2021: Valuing Water. United Nations.
8. UNEP. (2018). Progress on Water Quality: Global Status and Acceleration Needs for SDG Indicator 6.3.2. United Nations Environment Programme.
9. WHO. (2017). Guidelines for Drinking-water Quality. World Health Organization.
10. WHO. (2019). Water, Sanitation, Hygiene and Health: A Primer for Health Professionals. World Health Organization.
11. Mishra, A. K., & Singh, V. P. (2010). A Review of Drought Concepts. Journal of Hydrology, 391(1-2), 202-216.
12. Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
13. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
14. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media.
15. Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. Springer.