Abstract
In this paper, multiple linear regression (MLR) and radial basis function neural network (RBF-NN) are applied to predict nitrate (NO3-) concentration with and without reservoir volume (WV) as predictor using monthly data for ten years in three water reservoirs located in the upper Cheliff basin (NW of Algeria). The datasets were divided into training (80%) and testing (20%) sets and two different scenarios were compared. The results revealed that RBF-NN was more efficient (MAE = 0.192 and SI = 0.061) compared with the MLR model to predict NO3- in all reservoirs. RBF-NN provided the best accuracy in the testing period with a high R2 of 0.957 in reservoir II, and low MSE and PBias of 0.048 mg/l and 2.98% in the training period in reservoir III, respectively. Overall, the best results were generated by M(iii) in scenario B.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Author contributions
Ibrahim Mehdaoui: Writing the original draft, Conceptualization, and Formal analysis; Bachir Sakaa: Writing review and editing; Samir Boudibi: Mapping and Software modeling; Hicham Chaffai: conceptualization; Azzedine Hani: Interpretation of the results; Sarmad Dashti Latif: Writing review and editing.
Additional information
Notes on contributors
Ibrahim Mehdaoui
Mr. Ibrahim Mehdaoui is a PhD student in the department of Geology at Annaba University. His dissertation entitled: The use of Stochastic models for water resources management in Chéliff River Basin (North-West of Algeria).
Samir Boudibi
Dr. Boudibi Samir holds a doctorate (PhD) in hydropedology in arid regions from the University of Mohamed Khider of Biskra, Algeria in 2021. He is actually a researcher at the Scientific and Technical Research Center on Arid Regions (CRSTRA), Biskra, Algeria. His research interest includes smart irrigation and drainage systems, groundwater quality, soil salinity, remote sensing, spatial analysis and kriging as well as the application of machine learning in water and soil-related systems.
Sarmad Dashti Latif
Mr. Sarmad Dashti Latif received Bachelor Degree in Civil Engineering with first-class honours in 2018 at Universiti Tenaga Nasional (UNITEN), Malaysia. He received Master of Civil Engineering by research in the field of water resources engineering in 2021 at the Universiti Tenaga Nasional (UNITEN), Malaysia. Previously, he was working as a research officer and tutor at Universiti Tenaga Nasional (UNITEN). Currently, he is working as lecturer and research fellow at Civil Engineering Department in Komar University of Science and Technology in Kurdistan region of Iraq. He is the author of more than 30 scientific articles and a book published in prestigious international journals. His research interests include the application of artificial intelligence (AI) techniques with their applications such as Machine Learning and Deep Learning methods for many engineering applications and concentrate on hydrological processes, environmental and water management, operation of dams and reservoirs. Currently, his research focuses on achieving water security in Kurdistan Region of Iraq.
Bachir Sakaa
Prof. Bachir Sakaa earned a PhD degree in June of 2013 in Water Resources Management from Annaba University. He started working at the Scientific and Technical Research Centre on AridAreas C.R.S.T.R.A in May of 2011. Currently, Bachir is working at the Water Resources and Land Degradation Department. His areas of interest include hydrogeology, water quality, hydrology and machine learning models.
Hicham Chaffai
Prof. Hicham Chaffai is a Full Professor at Annaba University inthe Department of Geology. He conducts research to solve complex problems associated with environmental pollution. Her main research interests include Hydro geological and hydrological modeling, water quality and pollution.
Azzedine Hani
Prof. Azzedine Hani is a Full Professor at Annaba University in the Department of Geology. Mr Azzedine has over 19 years of hydrogeology and water management experience. His areas of interest include water resources management, water pollution, environmental assessment and modelling.