Deep Spatiotemporal Learning for Multivariate Water Quality Prediction: Temporal Dynamics–Aware CNN–GRU Hybrid Model

Year 2025, Volume: 6 Issue: 2, 32 - 41, 30.12.2025

Esen Damla Balo Utku , Banu Kutlu

Abstract

Proper forecasting of water quality indicators is one of the most important factors in sustainable environmental management, protecting ecosystems, and early detection of potential pollution risks. Among them, pH is essential for regulating chemical and biological processes in water and can be significantly altered by natural and man-made factors. Water quality parameters are also nonlinear, multivariate, and time-varying, which makes it challenging to estimate pH in modeling. In this paper, we develop a deep learning-based approach to predicting next-day pH using multivariate time-series water-quality measurements from different monitoring stations. The hybrid CNNGRU architecture is developed in this work in which the short-term temporal patterns of the multivariate water-quality sequences can be obtained through the convolutional layers, whereas the long-term temporal dependencies are learned by the GRU units. Several machine learning models and deep learning models, such as classical ensembles, recurrent neural networks, and hybrids, are designed to learn the complex temporal dynamics of the data. To be more precise, a spatiotemporal modeling framework based on a hybrid Convolutional Neural Network and Gated Recurrent Unit design is developed to reveal the local-temporal dynamics and long-term associations of the variables of water quality under consideration. Many experiments are conducted to assess the predictive accuracy of all models using standard error and agreement measures under normal conditions. According to the results of the experiments, the proposed CNN-GRU always performs better in comparison to classical machine learning (as well as stand-alone deep learning) models in terms of RMSE, MAE, R2, and WI. Experimental studies indicate that hybrid deep learning models achieve substantial gains over classical pH estimation methods. The findings indicate that convolutional feature extraction combined with recurrent temporal modeling can be essential for modeling the dynamic nature of water quality systems.

Keywords

Water quality , pH , spatiotemporal modelling , deep learning , machine learning

References

• Chapman, D. V., and Sullivan, T. (2022). The role of water quality monitoring in the sustainable use of ambient waters. One Earth, 5(2), 132-137.
• Gaines, M. D., Tulbure, M. G., and Perin, V. (2022). Effects of climate and anthropogenic drivers on surface water area in the southeastern United States. Water Resources Research, 58(3), e2021WR031484.
• Pinheiro, J. P. S., Windsor, F. M., Wilson, R. W., and Tyler, C. R. (2021). Global variation in freshwater physico‐chemistry and its influence on chemical toxicity in aquatic wildlife. Biological Reviews, 96(4), 1528-1546.
• Ibrahim, U., Abbas, N., Riaz, M., and Mahmood, T. (2025). Smart Monitoring Solutions for Real‐Time Water pH Regulation in Aquatic Ecotoxicology. Journal of Chemometrics, 39(4), e70024.
• Chen, J., Chen, S., Fu, R., Li, D., Jiang, H., Wang, C., and Hicks, B. J. (2022). Remote sensing big data for water environment monitoring: Current status, challenges, and future prospects. Earth's Future, 10(2), e2021EF002289.
• Liu, X., Lu, D., Zhang, A., Liu, Q., and Jiang, G. (2022). Data-driven machine learning in environmental pollution: gains and problems. Environmental science and technology, 56(4), 2124-2133.
• Ahmed, D. M., Hassan, M. M., and Mstafa, R. J. (2022). A review on deep sequential models for forecasting time series data. Applied computational intelligence and soft computing, 2022(1), 6596397.
• Chen, B., Mu, X., Chen, P., Wang, B., Choi, J., Park, H., and Yang, H. (2021). Machine learning-based inversion of water quality parameters in typical reach of the urban river by UAV multispectral data. Ecological Indicators, 133, 108434.
• Khoi, D. N., Quan, N. T., Linh, D. Q., Nhi, P. T. T., and Thuy, N. T. D. (2022). Using machine learning models for predicting the water quality index in the La Buong River, Vietnam. Water, 14(10), 1552.
• Haq, K. R. A., and Harigovindan, V. P. (2022). Water quality prediction for smart aquaculture using hybrid deep learning models. IEEE Access, 10, 60078-60098.
• Wu, X., Zhang, Q., Wen, F., and Qi, Y. (2022). A water quality prediction model based on multi-task deep learning: a case study of the Yellow River, China. Water, 14(21), 3408.
• Qian, J., Liu, H., Qian, L., Bauer, J., Xue, X., Yu, G., and Norra, S. (2022). Water quality monitoring and assessment based on cruise monitoring, remote sensing, and deep learning: A case study of Qingcaosha Reservoir. Frontiers in Environmental Science, 10, 979133.
• Huan, J., Liao, W., Zheng, Y., Xu, X., Zhang, H., and Shi, B. (2023). A deep learning model with spatio-temporal graph convolutional networks for river water quality prediction. Water Supply, 23(7), 2940-2957.
• Ehteram, M., Ahmed, A. N., Sherif, M., and El-Shafie, A. (2024). An advanced deep learning model for predicting water quality index. Ecological Indicators, 160, 111806.
• Internet: Water Quality Prediction Dataset, In Kaggle Online. (2023). https://www.kaggle.com/datasets/parmajha/water-quality-prediction-dataset
• Öklü, M., and Canbay, P. (2023). Makine öğrenmesi yöntemleri ile şehirlerin hava kalitesi tahmini. International Journal of Advances in Engineering and Pure Sciences, 35(1), 39-53.
• Zhou, Z., Qiu, C., and Zhang, Y. (2023). A comparative analysis of linear regression, neural networks and random forest regression for predicting air ozone employing soft sensor models. Scientific Reports, 13(1), 22420.
• Du, K. L., Jiang, B., Lu, J., Hua, J., and Swamy, M. N. S. (2024). Exploring kernel machines and support vector machines: Principles, techniques, and future directions. Mathematics, 12(24), 3935.
• Najafzadeh, M., and Niazmardi, S. (2021). A novel multiple-kernel support vector regression algorithm for estimation of water quality parameters. Natural Resources Research, 30(5), 3761-3775.
• Wang, X., Mazumder, R. K., Salarieh, B., Salman, A. M., Shafieezadeh, A., and Li, Y. (2022). Machine learning for risk and resilience assessment in structural engineering: Progress and future trends. Journal of Structural Engineering, 148(8), 03122003.
• Demir, S., and Sahin, E. K. (2023). An investigation of feature selection methods for soil liquefaction prediction based on tree-based ensemble algorithms using AdaBoost, gradient boosting, and XGBoost. Neural Computing and Applications, 35(4), 3173-3190.
• Zhou, W., Zheng, Y., Pan, Z., and Lu, Q. (2021). Review on the battery model and SOC estimation method. Processes, 9(9), 1685.
• Namdari, H., Haghighi, A., and Ashrafi, S. M. (2025). Short-term urban water demand forecasting; application of 1D convolutional neural network (1D CNN) in comparison with different deep learning schemes. Stochastic Environmental Research and Risk Assessment, 39(10), 4211-4226.
• Utku, A., Kaya, M., and Canbay, Y. (2025). A New Hybrid ConvViT Model for Dangerous Farm Insect Detection. Applied Sciences, 15(5), 2518.
• Ouma, Y. O., Cheruyot, R., and Wachera, A. N. (2022). Rainfall and runoff time-series trend analysis using LSTM recurrent neural network and wavelet neural network with satellite-based meteorological data: case study of Nzoia hydrologic basin. Complex and Intelligent Systems, 8(1), 213-236.
• Gorgij, A. D., Askari, G., Taghipour, A. A., Jami, M., and Mirfardi, M. (2023). Spatiotemporal forecasting of the groundwater quality for irrigation purposes, using deep learning method: long short-term memory (LSTM). Agricultural Water Management, 277, 108088.
• Zarzycki, K., and Ławryńczuk, M. (2021). LSTM and GRU neural networks as models of dynamical processes used in predictive control: A comparison of models developed for two chemical reactors. Sensors, 21(16), 5625.
• Xu, J., Wang, K., Lin, C., Xiao, L., Huang, X., and Zhang, Y. (2021). FM-GRU: A time series prediction method for water quality based on seq2seq framework. Water, 13(8), 1031.
• Utku, A. (2024). Deprem Seviye Siniflandirmasi Için Hibrit Bir Convlstm Modeli: Karşilaştirmali Bir Analiz. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(4), 1334-1349.
• Sinha, P., Sahu, D., Prakash, S., Yang, T., Rathore, R. S., and Pandey, V. K. (2025). A high performance hybrid LSTM CNN secure architecture for IoT environments using deep learning. Scientific Reports, 15(1), 9684.
• Lalwani, P., and Ganeshan, R. (2024). A novel CNN-BiLSTM-GRU hybrid deep learning model for human activity recognition. International Journal of Computational Intelligence Systems, 17(1), 278.
• Singh, V., Sahana, S. K., and Bhattacharjee, V. (2025). A novel CNN-GRU-LSTM based deep learning model for accurate traffic prediction. Discover Computing, 28(1), 38.
• Chicco, D., Warrens, M. J., and Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj computer science, 7, e623.
• Piotrowski, P., Rutyna, I., Baczyński, D., and Kopyt, M. (2022). Evaluation metrics for wind power forecasts: A comprehensive review and statistical analysis of errors. Energies, 15(24), 9657.
• Martin, G. P., Riley, R. D., Collins, G. S., and Sperrin, M. (2021). Developing clinical prediction models when adhering to minimum sample size recommendations: The importance of quantifying bootstrap variability in tuning parameters and predictive performance. Statistical Methods in Medical Research, 30(12), 2545-2561.
• Yaseen, Z. M., Ali, M., Sharafati, A., Al-Ansari, N., and Shahid, S. (2021). Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh. Scientific reports, 11(1), 3435.