Determine Rate of Contamination in Tigris River in River Baghdad city by Artificial Intelligence
Keywords:
Tigris River, Contamination, Heavy metals, Artificial Intelligence, Artificial neural networks.Abstract
In this article, we used type of artificial intelligence that is suggest efficient design of artificial neural network ANN of type Feed Forward Neural Network (FFNN) based on new LM training algorithm. Then we used to determine the rate of contamination in Tigris River in Baghdad city. Architectural of design consist 4 layers: input layer contains 8 nodes represent: (PH, Total dissolve solids (T.D.S) Electrical Connection (EC), Total suspended solids (T.S.S), Chemical oxygen demanding (COD), Oil, Nephelometric Turbidity Unit) NTU (, Nitrate (NO)), 1st hidden layer contain 17 nodes, 2nd hidden layer contain 8 nodes with tansig. transfer function for each hidden layers and output layer contains 5 nodes for which are (Cd, Mg, pb, Fe, Cr), with linear transfer function. We used 100 sample distributed as 65 sample for training FFNN, 20 sample for testing and 15 sample for validation and the proposed FFNN achieved high predictive accuracy, with a minimum mean square error (MSE) of 2.47×10⁻⁵ and a final performance gradient of 1.57×10⁻⁵, indicating excellent convergence. The model successfully predicted the concentrations of heavy metals with an error less than 0.0012, which is considered scientifically acceptable for environmental assessments. Comparison between laboratory results and ANN outputs showed strong agreement, confirming the reliability of the model.
References
Abdulkareem, I. A., Abbas, A. A., & Dawood, A. S. (2022). Modeling pollution index using artificial neural network and multiple linear regression coupled with genetic algorithm. Journal of Ecological Engineering, 23(3), 236–250.
Al-Ani, R. R., Abdul Hameed, M., Al-Obaidy, J., & Badri, R. M. (2014). Assessment of Tigris water quality in the Baghdad–Iraq. International Journal of Advanced Research, 2(5), 1125–1131.
Al-layla, S. Z. M., Al-Ogaidi, A. A. M. (2025). A Comprehensive and Extensive Review of the Process of Water Infiltration in Soil. Journal of Water Resources and Geosciences. 4(2), 109 – 158. https://jwrg.gov.iq/index.php/jwrg/article/view/138/82
Allawi, M. F., Salih, S. Q., Kassim, M., Ramal, M. M., Mohammed, A. S., & Yaseen, Z. M. (2022). Application of computational model based probabilistic neural network for surface water quality prediction. Mathematics, 10(3960). https://doi.org/10.3390/math10213960.
Ghazi, F. F. (2018). Estimation of heavy metals contamination in soil of Zaafaraniya City using the neural network. Journal of Physics: Conference Series, 1003(1), 012058.
Ghazi, F. F. (2020). Modeling the contamination of soil adjacent to Mohammed ALQassim Highway in Baghdad. Iraqi Journal of Science, 61(10), 2663–2670. https://doi.org/10.24996/ijs.2020.61.10.23 .
Huynh, T.-M.-T., Ni, C.-F., Su, Y.-S., Nguyen, V.-C.-N., Lee, I.-H., Lin, C.-P., & Nguyen, H.-H. (2022). Predicting heavy metal concentrations in shallow aquifer systems based on low-cost physiochemical parameters using machine learning techniques. International Journal of Environmental Research and Public Health, 19(12180). https://doi.org/10.3390/ijerph1912180 .
Ibrahim, M. A., Mohammed-Ridha, M. J., Hussein, H. A., & Faisal, A. A. H. (2020). Artificial neural network modeling of the water quality index for the Euphrates River in Iraq. Iraqi Journal of Agricultural Sciences, 51(6), 1572–1580.
Isaev, V. A., & Mikhailova, M. V. (2009). The hydrology, evolution, and hydrological regime of the mouth area of the Shatt al-Arab River. Water Resources, 36(4), 380–395.
Ismael, A. N., Abed, H. A., & Abed, M. A. (2020). Classification of groundwater quality using artificial neural networks in Safwan and Al-Zubayr in Basra. Advances in Computer, Signals and Systems, 4(1), 25–35. Clausius Scientific Press. https://doi.org/10.23977/acss.2020.040105 .
Jasim, H. K., Tayyeh, H. K., Hussein, A. M. (2025). Studying the Effects of Heavy Metals Concentrations on selected Water Treatment Plants in Babylon Governorate. Journal of Water Resources and Geosciences. 4(1), 28 – 44. https://jwrg.gov.iq/index.php/jwrg/article/view/116/62
Mark, H. B., Martin, T. H., & Howard, B. D. (2017). Neural Network Toolbox™ user’s guide R2017b. The MathWorks, Inc.
Marquardt, D. W. (1963). An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2), 431–441.
Mohammed, M. N., & Tawfiq, L. N. M. (2010). The effect of number of training samples for artificial neural network. Ibn Al-Haitham Journal for Pure and Applied Science, 23(3), 1–7.
Oraibi, Y. A. (2013). Fast training algorithms for feed forward neural networks. Ibn Al-Haitham Journal for Pure and Applied Science, 26(1), 275–280.
Tawfiq, L. N. M., & Ghazi, F. F. (2015). Using artificial neural network technique for the estimation of Cd concentration in contaminated soils. International Journal of Innovations in Scientific Engineering, 1(1), 58–68.
Tawfiq, L. N. M., & Hassan, M. A. (2018). Estimate the effect of rainwaters in contaminated soil by using Simulink technique. Journal of Physics: Conference Series, 1003(1), 012057.
Tawfiq, L. N. M., & Hasan, M. A. (2019). Evaluate the rate of pollution in soil using Simulink environment. Ibn Al-Haitham Journal for Pure and Applied Science, 32(1), 132–138.
Tawfiq, L. N. M., & Khamas, A. H. (2023). New approach for calculate exponential integral function. Iraqi Journal of Science, 64(8), 4034–4042. https://doi.org/10.24996/ijs.2023.64.8.27 .
The Iraqi Ministry of Health and Environment. (n.d.). Results of laboratory tests performed by the Iraqi Ministry of Health and Environment for the Tigris River.
Yadav, N., Yadav, A., & Kumar, M. (2015). An introduction to neural network methods for differential equations. Springer. https://doi.org/10.1007/978-94-017-9816-7 .
