Explainable Transfer Learning Framework for Water Quality Prediction in Data-Scarce Developing Regions

Safe drinking water access continues to be a preva-lent public health challenge for developing nations, in which continuous water quality monitoring becomes infeasible due to the lack of resources, laboratory facilities, and sensors. Machine learning methods have been successfully applied for predicting water quality metrics such as dissolved oxygen (DO), turbidity, and pH. Nonetheless, traditional supervised machine learning models require sufficient amounts of labeled data (greater than 1000 instances) for optimal generalization. Due to the data-scarcity problem, only 100–200 historical instances are usually available for training. As a result, overfitting becomes inevitable. This paper proposes an Explainable Transfer Learning (XTL) approach for water quality prediction called XTL-WQ. We intro-duce three techniques: (i) a pre-trained Long Short-Term Mem-ory (LSTM) model; (ii) Maximum Mean Discrepancy (MMD) for domain adaptation; and (iii) SHapley Additive exPlanations (SHAP) for interpretability. On DO prediction, we achieve an RMSE of 0.42 mg/L with XTL-WQ, compared to 0.61 mg/L for LSTM baseline (+31% improvement). Under extreme data scarcity (less than 30 instances), our model achieves an RMSE of 0.51, while baselines exceed 0.75 mg/L.

Learning, Framework, Water Quality

1. Pan, S. J., and Yang, Q., “A survey on transfer learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, 2010. [Google Scholar] [Crossref]

2. Lundberg, S. M., and Lee, S. I., “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774, 2017. [Google Scholar] [Crossref]

3. Gretton, A., Borgwardt, K. M., Rasch, M. J., Scho¨lkopf, B., and Smola, A., “A kernel two-sample test,” Journal of Machine Learning Research, vol. 13, pp. 723–773, 2012. [Google Scholar] [Crossref]

4. Fig. 36. Comprehensive XTL-WQ performance dashboard summarizing model evaluation metrics, prediction performance, domain adaptation results, and explainability analysis. [Google Scholar] [Crossref]

5. Hochreiter, S., and Schmidhuber, J., “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [Google Scholar] [Crossref]

6. Ribeiro, M. T., Singh, S., and Guestrin, C., “Why should I trust you? Explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144, 2016. [Google Scholar] [Crossref]

7. Rudin, C., “Stop explaining black box machine learning models for high stakes decisions,” Nature Machine Intelligence, vol. 1, no. 5, pp. 206–215, 2019. [Google Scholar] [Crossref]

8. Kargar, K., Sadeghian, A., and Nasseri, M., “Data scarcity in water quality modeling: A systematic review,” Environmental Modelling & Software, vol. 133, pp. 104–118, 2020. [Google Scholar] [Crossref]

9. Wang, H., Zhao, Y., and Chen, L., “Transfer learning for water quality prediction in unmonitored catchments,” Water Research, vol. 212, pp. 118–127, 2022. [Google Scholar] [Crossref]

10. Ahmed, A. N., Othman, F. B., and Afan, H. A., “Machine learning for water quality classification,” Journal of Hydrology, vol. 579, pp. 124–136, 2019. [Google Scholar] [Crossref]

11. Liu, P., and Chen, X., “Comparative analysis of machine learning models for water quality prediction with limited data,” Environmental Science and Pollution Research, vol. 28, no. 34, pp. 46822–46835, 2021. [Google Scholar] [Crossref]

12. Zhao, L., Li, X., and Wang, J., “Domain adaptation for soil moisture estimation using transfer learning,” Remote Sensing of Environment, vol. 245, pp. 111–124, 2020. [Google Scholar] [Crossref]

13. Xu, Y., Liu, H., and Wang, Z., “Transfer learning for air quality prediction across cities,” Environmental Research Letters, vol. 13, no. 8, pp. 084–092, 2018. [Google Scholar] [Crossref]

14. Chen, J., Zhang, D., and Yang, K., “Interpretable machine learning for groundwater arsenic prediction,” Water Resources Research, vol. 57, no. 6, p. e2020WR028124, 2021. [Google Scholar] [Crossref]

15. Ghobadi, F., and Kang, D., “A review of explainable artificial intelli-gence applications in water quality modeling,” Environmental Modelling & Software, vol. 157, pp. 105–118, 2022. [Google Scholar] [Crossref]

16. Zhang, Y., Li, C., and Wang, H., “LSTM with attention mechanism for water quality prediction,” Journal of Hydrology, vol. 598, pp. 126–138, 2021. [Google Scholar] [Crossref]

17. Breiman, L., “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [Google Scholar] [Crossref]

18. Long, M., Zhu, H., Wang, J., and Jordan, M. I., “Unsupervised domain adaptation by backpropagation,” in International Conference on Machine Learning, pp. 1–9, 2015. [Google Scholar] [Crossref]

19. Drucker, H., Burges, C. J., Kaufman, L., Smola, A., and Vapnik, V., [Google Scholar] [Crossref]

20. “Support vector regression machines,” in Advances in Neural Informa-tion Processing Systems, vol. 9, pp. 155–161, 1997. [Google Scholar] [Crossref]

21. Chen, T., and Guestrin, C., “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference, pp. 785–794, 2016. [Google Scholar] [Crossref]

22. Kingma, D. P., and Ba, J., “Adam: A method for stochastic optimiza-tion,” in International Conference on Learning Representations, pp. 1–15, 2015. [Google Scholar] [Crossref]

23. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhut-dinov, R., “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014. [Google Scholar] [Crossref]

24. Tibshirani, R., “Regression shrinkage and selection via the lasso,” Journal of the Royal Statistical Society Series B, vol. 58, no. 1, pp. 267–288, 1996. [Google Scholar] [Crossref]

25. Zou, H., and Hastie, T., “Regularization and variable selection via the elastic net,” Journal of the Royal Statistical Society Series B, vol. 67, no. 2, pp. 301–320, 2005. [Google Scholar] [Crossref]

26. Bengio, Y., “Practical recommendations for gradient-based training of deep architectures,” in Neural Networks: Tricks of the Trade, pp. 437–478, 2012. [Google Scholar] [Crossref]

27. Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning. MIT Press, 2016. [Google Scholar] [Crossref]

28. Chollet, F., Deep Learning with Python. Manning Publications, 2017. [Google Scholar] [Crossref]

29. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [Google Scholar] [Crossref]

30. United Nations Children’s Fund (UNICEF), “Progress on household drinking water, sanitation and hygiene 2000–2022: Special focus on gender,” WHO/UNICEF Joint Monitoring Programme, 2023. [Google Scholar] [Crossref]

31. World Health Organization, Guidelines for Drinking-Water Quality (4th ed.). WHO Press, 2022. [Google Scholar] [Crossref]

32. United Nations, “Sustainable Development Goal 6: Clean water and sanitation progress report,” United Nations Publications, 2023. [Google Scholar] [Crossref]

• Enhancing Formation Control of Multi Agent Systems Using Ann Based Technique
• Improving Sliding Mode Control with Chattering Reduction using Fuzzy Based Technique
• Cooking Quality, Fasting Blood Glucose, Glycemic Index and Load of High–Fiber Noodles Made from Wheat, Tiger Nut Residue and Cassava Flour Blends
• Matrix Rhythm Therapy Versus Interferential Therapy Combined with Lumbar Stabilization Exercises in Chronic Non-Specific Low Back Pain: A Randomized Comparative Trial
• Formulation and Sensory Evaluation of Functional Cake Prepared from Sweet Potato Powder