Unsupervised Classification of Water Quality Using Artificial Intelligence: The Case of the Moulouya Wadi's Surface Waters (NE, Morocco)

Abstract:

Due to its cruciality, water requires a high care to its physicochemical and microbiological properties to ensure the quality of several utilizations. The particles it carries are likely to be ingested, breathed, or come into contact with the skin. For the classification of the quality of surface water in the Moulouya River (NE, Morocco), this study presents many unsupervised classification methods. The overall quality of surface water in the Moulouya River in northeast Morocco was assessed using nine physicochemical parameters (pH, T°C, EC, O₂-diss, NH₄⁺, NO₃^-, SO₄^2-, PO₄^3-, and biological oxygen demand after 5 days (BOD₅)) from March to August 2014. Over a 600-kilometer stretch, twenty-two sites were examined, from the river's source in the High Atlas to its mouth in the Mediterranean. During the first stage, three quality classes (excellent, good and poor) were defined by the calculation of the water quality index (WQI) and water quality evaluation system (QES-Water). In the second stage, the K-means algorithm, the fuzzy C-means algorithm and the self-organizing maps (SOM) of Kohonen were applied to the nine physicochemical parameters used as input variables for the model. The classification method used is capable of projecting high-dimensional data into a lower dimension, typically 2D. This nonlinear projection can be useful in classes’ analysis and their discovery. In terms of performance, the SOM classification showed very close results compared to the K-means and the fuzzy C-means algorithms, with only an insignificant difference across the three models, with SOM maps having a slight advantage.

• Periodical: International Journal of Engineering Research in Africa (Volume 63)
• Pages: 83-95
• DOI: https://doi.org/10.4028/p-6lm8z8
• Online since: March 2023
• Authors: Taj Eddine Manssouri, Imad Manssouri*, Abdellah El Hmaidi, Hassane Sahbi, Othmane Noureddine
• Keywords: Artificial Intelligence, Moulouya River, Physico-Chemical Analysis, Quality, Unsupervised Classification

References

[1] Bouquet, C. (2011). Conflits et risques de conflits liés à l'eau en Afrique. Les Cahiers d'Outre-Mer. Revue de géographie de Bordeaux, 64(255), 341-362.

DOI: 10.4000/com.6283

[2] Auclair, A., & Lasserre, F. (2013). Aménagements, politiques et conflits sur l'eau en Afrique de l'Ouest. [VertigO] La revue électronique en sciences de l'environnement, 13(2).

DOI: 10.4000/vertigo.13994

[3] Avdeev, A., Eremenko, T., Festy, P., Gaymu, J., Le Bouteillec, N. & Springer, S. (2011). Populations et tendances démographiques des pays européens (1980-2010). Population, vol. 66(1), 9-133.

DOI: 10.3917/popu.1101.0009

[4] United Nations (2007). World Population Prospects: the 2006 Revision. http://esa. un.org/unpp/.

[5] El Hmaidi, A., Talhaoui, A., Manssouri, I., Jaddi, H., Ben-Daoud, M., Kasse, Z., ... & Essahlaoui, A. (2022). Assessment of the physicochemical water quality of the Moulouya River, Morocco, using the SEQ-Eau index. Environmental monitoring and assessment, 194(1), 1-17.

DOI: 10.1007/s10661-021-09636-4

[6] Manssouri, I., Talhaoui, A., El Hmaidi, A., Boudad, B., Boudebbouz, B., & Sahbi, H. (2021). Artificial intelligence for supervised classification purposes: Case of the surface water quality in the Moulouya River, Morocco. Journal of Water and Land Development, 240-247.

[7] Riad S. (2003). Typologie et analyse hydrologique des eaux superficielles à partir de quelques bassins versants représentatifs du Maroc. Thèse en cotutelle. Univ. Sci. et Tech. Lille,Univ. Ibnou Zohr., Agadir, 147p.

[8] Ahamrouni J. (1996). Erosion hydrique dans le bassin versant de la Moulouya (Maroc Oriental) : Recherche des zones sources d'envasement de la retenue du barrage Mohamed V. Thèse de 3ème cycle, Université Cheikh Anta Diop, Faculté des Sciences et Techniques, Dakar, Sénégal, 147 p.

DOI: 10.23956/ijermt/v6n1/101

[9] Nasloubi M., (1993). Genèse et modélisation des minéralisations plombifère de la haute Moulouya (Maroc). Mémoire de maitrise, Université du Québec à Montréal, 107p.

[10] Amrani A. (2007). Apport des données couplées d'imagerie satellitaire Etm+ de landsat 7 et modèle numérique de terrain appliques à l'étude morphogénétique de la haute et moyenne Moulouya (Maroc). Thèse Faculté des Sciences Agdal de Rabat - Doctorat ou Doctorat National [559], 217p.

DOI: 10.21474/ijar01/4476

[11] El Hmaidi A., Talhaoui A., Manssouri I., Jaddi H., Ousmana H. (2020). Contribution of the pollution index and GIS in the assessment of the physico-chemical quality of the surface waters of Moulouya River (NE, Morocco). La Houille Blanche, 106 (3), 1–10

DOI: 10.1051/lhb/2020028

[12] Panda A, Pattnayak N. (2013). Coastal Water Pollution Index (CWPI) – a tool for assessing coastal water quality along the North East Coast of India. Int J Sci Eng Res 4(6): 6.

[13] Taybi A.F., Mabrouki Y., Berrahou A., Chaabane K. (2016). Évolution spatiotemporelle des paramètres physico-chimiques de la Moulouya. Journal of Materials and Environmental Science, 7 (1) (pp.272-284).

[14] AFNOR (1997). Qualité de l'eau. Recueil des normes françaises environnement. Tomes 1, 2,3 et 4. (1372 p).

[15] Rodier J., Bazin C., Broutin J.P., Chambon P., Champsaur H., Rodi L. (1996). L'analyse de l'eau naturelle, eaux résiduaires, eau de mer, 8ème édition, Dunod, Paris, France, 1383p.

[16] Macqueen J., (1967). Some methods for classification and analysis of multivariate observations. In In 5-th Berkeley Symposium on Mathematical Statistics and Probability, p.281–297.

[17] Azzaoui, H., Mansouri, I., & Elkihel, B. (2019). Methylcyclohexane Continuous Distillation Column Fault Detection Using Stationary Wavelet Transform and K-Means. In International Conference on Electronic Engineering and Renewable Energy (pp.399-411). Springer, Singapore.

DOI: 10.1007/978-981-13-1405-6_48

[18] El Alaoui M. and Ben-Azza H. (2017). New Initialization for Clustering Algorithms Combining Distance and Density. In Proceedings of the 2nd International Conference on Big Data, Cloud and Applications, New York, NY, USA, p.26:1–26:5.

DOI: 10.1145/3090354.3090381

[19] Azzaoui, H., Mansouri, I., & Elkihel, B. (2018). Methylcyclohexane Continuous Distillation Column Fault Detection Using Stationary Wavelet Transform & Fuzzy C-means. Materials Today: Proceedings, 13, 597-606.

DOI: 10.1016/j.matpr.2019.04.018

[20] Kohonen T., (2001). Self-organizing maps, 3ed. Springer-Verlag Berlin Heidelberg.

[21] Ros, J., Laurent, C., & Lefebvre, G. (2006). A cascade of unsupervised and supervised neural networks for natural image classification. In International Conference on Image and Video Retrieval, pp.92-101. Springer, Berlin, Heidelberg.

DOI: 10.1007/11788034_10

[22] Ros, J. & Laurent, C. (2006). Description of local singularities for image registration. In 18th International Conference on Pattern Recognition (ICPR'06) (Vol. 4, pp.61-64). IEEE.

DOI: 10.1109/icpr.2006.430

[23] Eng, G. K., & Ahmad, A. M. (2005). Malay speech recognition using self-organizing map and multilayer perceptron. In Proceedings of the postgraduate annual research seminar (p.233).

[24] Kato, T., Inoue, K., Takahashi, T., & Kono, Y. (2007, April). Automatic Fault Diagnosis Method of Electrical Machinery and Apparatus by Using Kohonen's Self-Organizing Map. In 2007 Power Conversion Conference-Nagoya (pp.1224-1229). IEEE.

DOI: 10.1109/pccon.2007.373122

[25] Aroui, T., Koubaa, Y., & Toumi, A. (2009). Clustering of the self-organizing map based approach in induction machine rotor faults diagnostics. Leonardo Journal of Sciences, 15, 1-14.

[26] Kaya, A., Germen, E., Ünlü, Ü., & Toprak, S. (2008). Fault Classification in Hermetic Compressors Using Self-Organizing Map. International Compressor Engineering Conference, Paper 1921. https://docs.lib.purdue.edu/icec/1921.

[27] Germen, E., Başaran, M., & Fidan, M. (2014). Sound based induction motor fault diagnosis using Kohonen self-organizing map. Mechanical Systems and Signal Processing, 46(1), 45-58.

DOI: 10.1016/j.ymssp.2013.12.002

[28] Alvarez-Guerra, E., Molina, A., Viguri, J. R., & Alvarez-Guerra, M. (2011). A SOM-based methodology for classifying air quality monitoring stations. Environmental Progress & Sustainable Energy, 30(3), 424-438.

DOI: 10.1002/ep.10474

[29] Berrada, M., El Hmaidi, A., Monyr, N., Abrid, D., Abdallaoui, A., Essahlaoui, A., & El Ouali, A. El. (2016). Self-organizing map for the detection of seasonal variations in Sidi Chahed Dam sediments (Northern Morocco). Hydrological Sciences Journal, 61(3), 628–635.

DOI: 10.1080/02626667.2014.964717

[30] Ousmana, H., EL Hmaidi, A., Berrada, M., Damnati, B. and Etebaai I., 2016, Application of the self organizing map method for the classification of the environmental quality of the lake systems in the moroccan middle atlas: lakes cases of Ifrah, Iffer and Afourgagh: LARHYSS Journal, 25, 49–65.

DOI: 10.1016/j.quaint.2011.09.028

[31] Talhaoui, A., Manssouri, I., El Hmaidi, A., Berrada, M., & Manssouri, T. (2016). Self- Organizing Topological Maps for Classification of the Hercynian Granitoids From Their Geochemical Characteristics: Case of the Aouli Pluton (High Moulouya, Morocco). 3ed International Conference on Recent Advances in Pure and Applied Mathematics (ICRAPAM), bodrum, turkey Abstract book, p.202. ISBN: 978-975-00211-3-8.