Estimating Groundwater Nitrate Concentration using Artificial Neural Networks

Document Type : Original Article

Authors
Amir Hossein Sayyahzadeh
Ebrahim Bahadorifar
Department of Civil Engineering, Faculty of Civil & Architecture, Malayer University, Malayer, Iran
Abstract
Groundwater contamination by nitrate is a growing global concern. The increasing dependence of human societies on groundwater for urban and agricultural uses requires accurate and continuous prediction of nitrate concentrations in different parts of aquifers. Artificial neural networks are one of the efficient tools for modeling nitrate concentrations in groundwater, but they face challenges in selecting appropriate input variables, optimizing network architecture, and data shortage. In this study, after selecting 16 physical and chemical water quality parameters as network inputs and nitrate as network output, several structures of multilayer perceptron neural networks (60 models) were evaluated. Also, in the network that had the highest correlation coefficient and the lowest root mean square error, sensitivity analysis and data adequacy test were performed. The results showed that the three-layer perceptron neural network is able to predict nitrate concentrations with a correlation coefficient of 0.94 and a root mean square error of 1.3. The results of the sensitivity analysis showed that removing any of the network inputs alone does not have a significant impact on the performance of the network for estimating nitrate concentration. According to the results of the data adequacy test, to achieve a neural network model for proper estimation of groundwater nitrate, at least 220 measurement samples of groundwater nitrate concentration are required in order to achieve the desired accuracy for nitrate estimation.

Keywords

Subjects

Alizadeh, M., Noori, R., Omidvar, B., Nohegar, A. and Pistre, S., 2024. Human health risk of nitrate in groundwater of Tehran–Karaj plain, Iran. Scientific Reports, 14(1), p.7830. https://doi.org/10.1038/s41598-024-58290-6
Al-Mahallawi, K., Mania, J., Hani, A. and Shahrour, I., 2012. Using of neural networks for the prediction of nitrate groundwater contamination in rural and agricultural areas. Environmental Earth Sciences, 65(3), pp.917-928. https://doi.org/10.1007/s12665-011-1134-5
Band, S.S., Janizadeh, S., Pal, S.C., Chowdhuri, I., Siabi, Z., Norouzi, A., Melesse, A.M., Shokri, M. and Mosavi, A., 2020. Comparative analysis of artificial intelligence models for accurate estimation of groundwater nitrate concentration. Sensors, 20(20), p.5763. https://doi.org/10.3390/s20205763
Banisheikholeslami, A. and Qaderi, F., 2024. A novel machine learning framework for predicting biogas desulfurization breakthrough curves in a fixed bed adsorption column. Bioresource Technology Reports, 25, p.101702. https://doi.org/10.1016/j.biteb.2023.101702
Benzer, S. and Benzer, R., 2018. Modelling nitrate prediction of groundwater and surface water using artificial neural networks. Politeknik Dergisi, 21(2), pp.321-325. https://doi.org/10.2339/politeknik.385434
Darwishe, H., Khattabi, J.E., Chaaban, F., Louche, B., Masson, E. and Carlier, E., 2017. Prediction and control of nitrate concentrations in groundwater by implementing a model based on GIS and artificial neural networks (ANN). Environmental earth sciences, 76(19), p.649. https://doi.org/10.1007/s12665-017-6990-1
Ebrahimi Ghadi, M., Qaderi, F. and Babanezhad, E., 2019. Prediction of mortality resulted from NO 2 concentration in Tehran by Air Q+ software and artificial neural network. International Journal of Environmental Science and Technology, 16, pp.1351-1368. https://doi.org/10.1007/s13762-018-1818-4.
Ebrahimi, M. and Qaderi, F., 2021. Determination of the most effective control methods of SO2 pollution in Tehran based on adaptive neuro-fuzzy inference system. Chemosphere, 263, p.128002. https://doi.org/10.1016/j.chemosphere.2020.128002
Ehteshami, M., Farahani, N.D. and Tavassoli, S., 2016. Simulation of nitrate contamination in groundwater using artificial neural networks. Modeling Earth Systems and Environment, 2(1), p.28. https://doi.org/10.1007/s40808-016-0080-3
Grout, L., Chambers, T., Hales, S., Prickett, M., Baker, M.G. and Wilson, N., 2023. The potential human health hazard of nitrates in drinking water: a media discourse analysis in a high-income country. Environmental health, 22(1), p.9. https://doi.org/10.1186/s12940-023-00960-5
Karimanzira, D., Weis, J., Wunsch, A., Ritzau, L., Liesch, T. and Ohmer, M., 2023. Application of machine learning and deep neural networks for spatial prediction of groundwater nitrate concentration to improve land use management practices. Frontiers in Water, 5, p.1193142. https://doi.org/10.3389/frwa.2023.1193142
Karimanzira, D., 2024. Probabilistic Uncertainty Consideration in Regionalization and Prediction of Groundwater Nitrate Concentration. Knowledge, 4(4), pp.462-480. https://doi.org/10.3390/knowledge4040025
Lee, J.M., Ko, K.S. and Yoo, K., 2023. A machine learning-based approach to predict groundwater nitrate susceptibility using field measurements and hydrogeological variables in the Nonsan Stream Watershed, South Korea. Applied Water Science, 13(12), p.242. https://doi.org/10.1007/s13201-023-02043-9
Maghrebi, M., Noori, R., Partani, S., Araghi, A., Barati, R., Farnoush, H. and Torabi Haghighi, A., 2021. Iran's groundwater hydrochemistry. Earth and Space Science, 8(8), p.e2021EA001793. https://doi.org/10.1029/2021EA001793
Mahboobi, H., Shakiba, A. and Mirbagheri, B., 2023. Improving groundwater nitrate concentration prediction using local ensemble of machine learning models. Journal of Environmental Management, 345, p.118782. https://doi.org/10.1016/j.jenvman.2023.118782
Mousavi, S.F. and Amiri, M.J., 2012. Modelling Nitrate Concentration of Groundwater Using Adaptive Neural-Based Fuzzy Inference System. Soil & Water Research, 7(2).
Mousavi, M., Qaderi, F. and Ahmadi, A., 2023. Spatial prediction of temporary and permanent hardness concentrations in groundwater based on chemistry parameters by artificial intelligence. International Journal of Environmental Science and Technology, 20(6), pp.6665-6684. https://doi.org/10.1007/s13762-023-04934-5
Noori, R., Hooshyaripor, F., Javadi, S., Dodangeh, M., Tian, F., Adamowski, J.F., Berndtsson, R., Baghvand, A. and Klöve, B., 2020. PODMT3DMS-Tool: proper orthogonal decomposition linked to the MT3DMS model for nitrate simulation in aquifers. Hydrogeology Journal, 28(3). https://doi.org/10.1007/s10040-020-02114-0
Ostad-Ali-Askari, K., Shayannejad, M. and Ghorbanizadeh-Kharazi, H., 2017. Artificial neural network for modeling nitrate pollution of groundwater in marginal area of Zayandeh-rood River, Isfahan, Iran. KSCE Journal of Civil Engineering, 21(1), pp.134-140. https://doi.org/10.1007/s12205-016-0572-8
Qaderi, F. and Babanezhad, E., 2017. Prediction of the groundwater remediation costs for drinking use based on quality of water resource, using artificial neural network. Journal of Cleaner Production, 161, pp.840-849. https://doi.org/10.1016/j.jclepro.2017.05.187
Salceda-Gonzalez, M., Udawatta, R.P. and Appold, M.S., 2025. Groundwater Nitrate-Nitrite Modeling in a Grazed Hillslope with Agroforestry and Grass Buffers. Water, 17(5), p.608. https://doi.org/10.3390/w17050608
Stylianoudaki, C., Trichakis, I. and Karatzas, G.P., 2022. Modeling groundwater nitrate contamination using artificial neural networks. Water, 14(7), p.1173. https://doi.org/10.3390/w14071173
Tian, D., Zhao, X., Gao, L., Jiang, T., Liang, Z., Yang, Z., Zhang, P., Wu, Q., Ren, K., Yang, C. and Li, R., 2025. A framework for tracing the sources of nitrate in surface water through remote sensing data coupled with machine learning. npj Clean Water, 8(1), pp.1-13. https://doi.org/10.1038/s41545-025-00473-3
Trichakis, I.C., Nikolos, I.K. and Karatzas, G.P., 2011. Artificial neural network (ANN) based modeling for karstic groundwater level simulation. Water Resources Management, 25, pp.1143-1152. https://doi.org/10.1007/s11269-010-9628-6