muhamad, A., Ali, F., Azeez, S., Pana, H. (2025). Machine Learning-Based Prediction of River Water Quality Using LSTM and RF Models with PCA and Stepwise Regression for Dimensionality Reduction: A Case Study of the Maroon River Basin. , 16(3), 152-165. doi: 10.58928/ku25.16318
ahmad majeed muhamad; Falah Hama Faraj Ali; Salim Neimat Azeez; Hiwa Faraj Pana. "Machine Learning-Based Prediction of River Water Quality Using LSTM and RF Models with PCA and Stepwise Regression for Dimensionality Reduction: A Case Study of the Maroon River Basin". , 16, 3, 2025, 152-165. doi: 10.58928/ku25.16318
muhamad, A., Ali, F., Azeez, S., Pana, H. (2025). 'Machine Learning-Based Prediction of River Water Quality Using LSTM and RF Models with PCA and Stepwise Regression for Dimensionality Reduction: A Case Study of the Maroon River Basin', , 16(3), pp. 152-165. doi: 10.58928/ku25.16318
muhamad, A., Ali, F., Azeez, S., Pana, H. Machine Learning-Based Prediction of River Water Quality Using LSTM and RF Models with PCA and Stepwise Regression for Dimensionality Reduction: A Case Study of the Maroon River Basin. , 2025; 16(3): 152-165. doi: 10.58928/ku25.16318

Machine Learning-Based Prediction of River Water Quality Using LSTM and RF Models with PCA and Stepwise Regression for Dimensionality Reduction: A Case Study of the Maroon River Basin

Kirkuk University Journal for Agricultural Sciences (KUJAS)
Volume 16, Issue 3, September 2025, Pages 152-165    PDF (897.29 K)
Document Type: Research Paper
DOI: 10.58928/ku25.16318
Authors
ahmad majeed muhamad1; Falah Hama Faraj Ali* 2; Salim Neimat Azeez3; Hiwa Faraj Pana4
1students
2Surveying Department, Darbandikhan Technical Institute, Sulaimani Polytechnic University, Sulaimani, KGR, Iraq,
3Protected Cultivation Department , Bakrajo Technical Institute, Sulaimani Polytechnic University, Sulaimani, KGR, IRAQ
4Civil Engineering and Architecture Faculty, Shahid Chamran University of Ahvaz, Ahvaz , IRAN
Abstract
Monitoring and predicting river water quality is crucial for urban water management, agriculture, and environmental sustainability, especially in hot and arid regions. The presence of dams along the river course can significantly alter water quality by affecting flow regimes and salt accumulation, potentially leading to increased salinity and other related problems. However, such changes can be effectively managed through accurate modeling and forecasting. This study assesses the performance of two machine learning models, Random Forest (RF) and Long Short-Term Memory (LSTM), in predicting electrical conductivity (EC) and sodium absorption ratio (SAR) within the Maroon River Basin, Iran. Principal Component Analysis (PCA) and stepwise regression were employed to reduce input dimensionality and enhance model efficiency. Results indicate that the LSTM model consistently outperforms RF at both Idank station (upstream of Maroon Dam) and Tang-e-Tekab station (downstream of Maroon Dam) for both parameters, particularly in SAR prediction. At Idank station, the LSTM model combined with stepwise regression achieved the highest accuracy for EC prediction, with an R² of 0.96, RMSE of 61.56, and KGE of 0.96 on the test dataset. For SAR at the same station, LSTM again demonstrated exceptional performance, attaining an R² of 0.99, RMSE of 0.08, and KGE of 0.99. At Tang-e-Tekab station, LSTM with PCA yielded the most precise EC predictions (R² = 0.96, RMSE = 76.60, KGE = 0.97). Similarly, the best SAR predictions at this station were obtained using LSTM with PCA (R² = 0.96, RMSE = 0.18, KGE = 0.95). These findings underscore the effectiveness of combining LSTM networks with tailored input selection techniques based on site-specific conditions, highlighting their potential application in water resource decision support systems. Overall, this study demonstrates that although dam operations influence water quality, such impacts can be successfully managed through advanced predictive modeling to facilitate sustainable water resources management.
Keywords
Maroon River; Water quality; EC; SAR; LSTM; Dimensionality reduction
References
  • Kaushal SS, Likens GE, Pace ML, Reimer JE, Maas CM, Galella JG, Utz RM, Duan S, Kryger JR, Yaculak AM, Boger WL. Freshwater salinization syndrome: from emerging global problem to managing risks. Biogeochemistry. 2021 Jun;154:255-92.
  • Al-Mukhtar M, Al-Yaseen F. Modeling Water Quality Parameters Using Data-Driven Models, a Case Study Abu-Ziriq Marsh in South of Iraq. Hydrology. 2019; 6(1):24. https://doi.org/10.3390/hydrology6010024
  • Adib A, Farajpanah H, Mahmoudian Shoushtari M, Ahmadeanfar I. Estimation of Water Quality Parameters in the Sepidrood River by ANFIS, GEP and LS-SVM Models. Journal of Water and Wastewater. 2020 Nov 21;31(5):1-0.
  • Adib A, Farajpanah H, Shoushtari MM, Lotfirad M, Saeedpanah I, Sasani H. Selection of the best machine learning method for estimation of concentration of different water quality parameters. Sustainable Water Resources Management. 2022 Dec;8(6):172.
  • Victoriano JM, Santos ML, Vinluan AA, Carpio JT. Predicting pollution level using random forest: a case study of Marilao River in Bulacan Province, Philippines. arXiv preprint arXiv:2202.06066. 2022 Feb 12.
  • Bui DT, Khosravi K, Tiefenbacher J, Nguyen H, Kazakis N. Improving prediction of water quality indices using novel hybrid machine-learning algorithms. Science of the Total Environment. 2020 Jun 15;721:137612.
  • Wu X, Zhang Q, Wen F, Qi Y. A water quality prediction model based on multi-task deep learning: a case study of the Yellow River, China. Water. 2022 Oct 27;14(21):3408.
  • Ubah JI, Orakwe LC, Ogbu KN, Awu JI, Ahaneku IE, Chukwuma EC. Forecasting water quality parameters using artificial neural network for irrigation purposes. Scientific Reports. 2021 Dec 24;11(1):24438.
  • Nouraki A, Alavi M, Golabi M, Albaji M. Prediction of water quality parameters using machine learning models: A case study of the Karun River, Iran. Environmental Science and Pollution Research. 2021 Oct;28(40):57060-72.
  • Trach R, Trach Y, Kiersnowska A, Markiewicz A, Lendo-Siwicka M, Rusakov K. A study of assessment and prediction of water quality index using fuzzy logic and ANN models. Sustainability. 2022 May 7;14(9):5656.
  • Adib A, Farajpanah H, Shoushtari MM, Lotfirad M, Saeedpanah I, Sasani H. Selection of the best machine learning method for estimation of concentration of different water quality parameters. Sustainable Water Resources Management. 2022 Dec;8(6):172.
  • Ibrahim A, Ismail A, Juahir H, Iliyasu AB, Wailare BT, Mukhtar M, Aminu H. Water quality modelling using principal component analysis and artificial neural network. Marine Pollution Bulletin. 2023 Feb 1;187:114493.
  • Adjovu GE, Stephen H, Ahmad S. A machine learning approach for the estimation of total dissolved solids concentration in lake mead using electrical conductivity and temperature. Water. 2023 Jul 2;15(13):2439.
  • Pourhosseini FA, Ebrahimi K, Omid MH. Prediction of total dissolved solids, based on optimization of new hybrid SVM models. Engineering Applications of Artificial Intelligence. 2023 Nov 1;126:106780.
  • Pyo J, Pachepsky Y, Kim S, Abbas A, Kim M, Kwon YS, Ligaray M, Cho KH. Long short-term memory models of water quality in inland water environments. Water research X. 2023 Dec 1;21:100207.
  • Karbasi M, Ali M, Bateni SM, Jun C, Jamei M, Farooque AA, Yaseen ZM. Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm. Scientific reports. 2024 Jul 1;14(1):15051.
  • Jaafer NS, Al-Mukhtar M. Prediction of Water Quality Parameters of Tigris River in Baghdad City by Using Artificial Intelligence Methods. Ecological Engineering & Environmental Technology. 2024;25.
  • Ismail R, Rawashdeh A, Al-Mattarneh H, Hatamleh R, Dua’a BT, Jaradat A. Artificial intelligence for application in water engineering: The use of ANN to determine water quality index in rivers. Civil Engineering Journal. 2024 Jul 1;10(7):2261-74.
  • Satish N, Anmala J, Rajitha K, Varma MR. A stacking ANN ensemble model of ML models for stream water quality prediction of Godavari River Basin, India. Ecological Informatics. 2024 May 1;80:102500.
  • Adnan RM, Ewees AA, Wang M, Kisi O, Heddam S, Parmar KS, Zounemat-Kermani M. Enhancing BOD5 forecasting accuracy with the ANN-Enhanced Runge Kutta model. Journal of Environmental Chemical Engineering. 2025 Apr 1;13(2):115430.
  • Khosravi K, Farooque AA, Karbasi M, Ali M, Heddam S, Faghfouri A, Abolfathi S. Enhanced water quality prediction model using advanced hybridized resampling alternating tree-based and deep learning algorithms. Environmental Science and Pollution Research. 2025 Feb 24:1-20.
  • Abushandi E. Water Quality Assessment and Forecasting Along the Liffey and Andarax Rivers by Artificial Neural Network Techniques Toward Sustainable Water Resources Management. Water. 2025 Feb 6;17(3):453.
  • Al-Khuzaie MM, Abdul Maulud KN, Wan Mohtar WH, Yaseen ZM. Modelling Euphrates river water quality index based on field measured data in Al-Diwaniyah City, Iraq. Scientific Reports. 2025 Jan 2;15(1):51.
  • Isık H, Akkan T. Water quality assessment with artificial neural network models: Performance comparison between SMN, MLP and PS-ANN methodologies. Arabian Journal for Science and Engineering. 2025 Jan;50(1):369-87.
  • Ahmadpour A, Mirhashemi SH, Panahi M. Comparative evaluation of classical and SARIMA-BL time series hybrid models in predicting monthly qualitative parameters of Maroon river. Applied Water Science. 2023 Mar;13(3):71.
  • Sayahi F, Divband Hafshejani L, Tishehzan P, Abdolabadi H. The combination of dimensionality reduction methods and machine learning algorithms in the optimization of Maroon River water quality prediction. Iranian Journal of Soil and Water Research. 2024 Nov 21;55(9):1601-15.
  • Farajpanah H, Adib A, Lotfirad M, Esmaeili-Gisavandani H, Riyahi MM, Zaerpour A. A novel application of waveform matching algorithm for improving monthly runoff forecasting using wavelet–ML models. Journal of Hydroinformatics. 2024 Jul 1;26(7):1771-89.
  • Breiman L. Random forests. Machine learning. 2001 Oct;45:5-32.
  • Salehinejad H, Sankar S, Barfett J, Colak E, Valaee S. Recent advances in recurrent neural networks. arXiv preprint arXiv:1801.01078. 2017 Dec 29.
  • Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997 Nov 15;9(8):1735-80.
  • Chen H, Yang J, Fu X, Zheng Q, Song X, Fu Z, Wang J, Liang Y, Yin H, Liu Z, Jiang J. Water quality prediction based on LSTM and attention mechanism: A case study of the Burnett River, Australia. Sustainability. 2022 Oct 14;14(20):13231.
  • Farajpanah H, Lotfirad M, Adib A, Esmaeili-Gisavandani H, Kisi Ö, Riyahi MM, Salehpoor J. Ranking of hybrid wavelet-AI models by TOPSIS method for estimation of daily flow discharge. Water Supply. 2020 Dec 1;20(8):3156-71.
  • Wright MN, Ziegler A, König IR. Do little interactions get lost in dark random forests?. BMC bioinformatics. 2016 Dec;17:1-0.
  • Lai G, Chang WC, Yang Y, Liu H. Modeling long-and short-term temporal patterns with deep neural networks. InThe 41st international ACM SIGIR conference on research & development in information retrieval 2018 Jun 27 (pp. 95-104).
  • Kratzert F, Klotz D, Shalev G, Klambauer G, Hochreiter S, Nearing G. Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets. Hydrology and Earth System Sciences. 2019 Dec 17;23(12):5089-110.
Statistics
Article View: 352
PDF Download: 377


Journal Management System. Powered by iJournalPro.com