Quantification of salinity using artificial neural networks. Case study of the Isser River (Algeria)

K. Houari


Abstract: In this study, we examine a very complex phenomenon in the salinity of rivers. The complexity of the mineralization of rivers makes it difficult to quantify by traditional statistical models. Artificial intelligence is an interesting and fully justified alternative for modeling non-linear phenomena. The present study aims to develop a model based on a multilayer perceptron neuron network (MLP), capable of explaining the salt concentration-liquid flow relationship. The method is based on observations recorded at the Oued Isser outlet at the Lakhdaria hydrometric. The obtained results indicate that the artificial neural network model (MLP) has the best performance compared to the empirical model, with an ''R2 '' value for regression analysis of training, testing and validation of 80%, 75% and 78%, respectively. Further, the «Nash» value for training, testing and validation are 79%, 72% and 75%, respectively.

Full Text:



Tessier, L. Transport and characterization of suspended matter in the watershed of the Seine: identification of natural and anthropogenic signatures, Doctoral Thesis (2003), Ecole nationale des Pont et Chaussées France.

Garrels, R.M.; Mackenzie, F.T. Evolution of sedimentary rocks, W.W. Norton and Company Inc., (1971), New York, 397 p.

Meybeck, M. Chemical composition of unpolluted French streams. Geological Sciences (1986).

Meybeck, M. Global chemical weathering of surfical rocks estimated from river dissolved loads. American Journal of Science, 5:287 (1987) 401-428.

Probst, J.L. Geochemistry and hydrology of continental mechanical erosion, current global balance, fluctuations over the last 500 million years, Doctoral thesis, University of Strasbourg, (1990) 323 p.

Touat, S. Methodology for the Study of the Salinity of Rivers, Report No. 5 (1992), 52-63. ANRN.

Wenrui, H,; Simon, F. Neural network modeling of salinity variation in Apalachicola River, Water Research, 36 (2002) 356-362.

Houari, K.; Hartani, T.; Remini, B.; Lefkir, A.; Abda L.; Heddam S. A hybrid model for modelling the salinity of the Tafna River in Algeria, Journal of Water and Land Development. 1:3 (2019) 127-135.

Benatiallah, D. ; Benatiallah A. ; Bouchouicha K. ; Nasri B. Predicting hourly solar radiation using artificial neuron networks, Algerian J. Env. Sc. Technology, 6 :1 (2020) 1236-1245.

Nemili, Z.; Kalla, M. Modeling of Bridge Scour by Artificial Neural Networks based on PCR, Algerian J. Env. Sc. Technology, 5:3 (2019) 1036 -1040.

Jang, J.S.R.; Suni, C.T.; Mizutani, E. Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence. IEEE transactions on automatic control, 42:10 (1997) 1482-1484.

Bouzeria, H.; Ghenim A.N.; Khanchoul, K. Using artificial neural network (ANN) for prediction of sediment loads, application to the Mellah catchment, northeast Algeria. Journal of Water and Land Development, 47:55 (2017) 47-55.

Tachi, S.E.; Ouerdachi L.; Remaoun, M.; Derdous, O.; Boutaghane H. Forecasting suspended sediment load using regularized neural network: Case study of the Isser River (Algeria), Journal of Water and Land Development, 75:81 (2016) 75-81.

ANRH. Application of a salinity calculation methodology to the Tafna watershed, (1996) report 1.

Terfous, A. ; Megnounif, A.; Bouanani, A. Study of solid transport in suspension in the Oued Mouilah (North-West Algeria), Journal of Water Science, 14:2 (2001).

Kerem, H.C.; Kisi, Ö. Methods to improve the neural network performance in suspended sediment estimation, Journal of Hydrology, 3:17 (2006) 221-238.

Erol, Keskin, M.; Dilek, T.; Özlem, T. Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series, Hydrological Sciences Journal, 51:4 (2006) 588-598.

Mellita, A.; Kalogirou, S. Artificial intelligence techniques for photovoltaic applications: A review, Progress in Energy and Combustion Science, 34:5 (2008) 574-632.

Chen, S.H.; Jakeman, A.J.; Norton, J.P. Artificial intelligence techniques: An introduction to their use for modelling environmental systems, Mathematics and Computers in Simulation, 2:3 (2008).

El Badaoui, H.; Abdallaoui, A. ; Chabaa, S. Perceptron Multilayers and radial basis function grating for moisture prediction, International Journal of Innovation and Scientific Research, 5:1 (2014) 55-67.

Vourkas, M.; Papadourakis, G. Effects of segmentation on the discrimination of three mental stages using ANN and different EEG signal representations, Proc. 4th Int. Con. Neural Networks and Expert Syst, (2001) 65-68.

Heddam, S.; Bermad, A.; Dechemi, N. Modeling of the coagulant dose by fuzzy inference-based systems (ANFIS) application to the Boudouaou water treatment station (Algeria), Journal of Water Science, 1:17 (2012).

Dreyfus, G.; Samuelides, M.; Martinez, J.; Gordon, M.; Badran, F.; Thiria, S.; Herault, L. Neural Networks-Methodologies and applications. Editions Eyrolles, Paris, France, (2004).

Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators, Neural Networks (1989) 359-366.

Hornik, K.; Stinchcombe, M.; White, H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks, Neural Networks, 3:5 (1990) 551-560.

Shafaei, M.; Adamowski, J.; Fakheri, F.A.; Dinpashoh, Y.; Adamowski, K. A wavelet-SARIMA-ANN hybrid model for precipitation forecasting, Journal of Water and Land Development, No. 28 (2016) 27-36.

Rajaee, T. Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models, Science of the Total Environment, 407 (2009) 4916-4927.

Nash, J.E.; Sutcliffe, J.V. River flow forecasting through conceptual model. Part 1. A discussion of principles, Journal of Hydrology, (1970) 282-290.

Zeggane, H. Study of the hydrological behavior of rivers in Algeria, case of the Isser watershed, Algeria. Doctoral thesis, Kasdi-Merbah Ouargla University (2017), 186 p.

Larfi, B.; Boualem, B. Solid transport in the Oued Isser watershed impacts the silting up of the Beni Amrane dam (Algeria), Larhyss Journal, n° 05 (2006) 63-73.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License. Copyright UMMB © 2020 University M'hamed Bougara - Boumerdes. Independance AV., Boumerdes, 35000 Algeria, Tel/Fax: +213 24 91 14 98/ +213 2491-29-51