Using Machine Learning Approaches to Predict Water Quality of Ibn Battuta Dam (Tangier, Morocco)

El Mustapha Azzirgue, Farida Salmoun, El Khalil Cherif, Taha Ait Tchakoucht, Nezha Mejjad

2021

Abstract

Ibn Batouta dam was built in 1977 next to catchment outlet and provides the Tangier-Assilah cities inhabitants with drinking water. The present study aims to assess the quality of Ibn Batouta dam water and use machine learning approaches to predict the future water quality of this dam. We select Dissolved Oxygen as the vital quality factor to be forecasted. A Long-short term memory (LSTM) network and a fully connected multilayer perceptron (MLP) are employed to predict Dissolved Oxygen in the next five years. The two models are assessed concerning, for data collected over twenty-one years (between 1998 and 2019) from Ibn Battuta station. The two models performances are compared and evaluated based on three metrics, Mean Square Error (MSE), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Experimental results show that LSTM outperforms MLP by reducing RMSE, MSE and MAE respectively by 87%, 98% and 88%, indicating that the LSTM model is more accurate in tackling time series.

Paper Citation

in Harvard Style

Azzirgue E., Salmoun F., Cherif E., Ait Tchakoucht T. and Mejjad N. (2021). Using Machine Learning Approaches to Predict Water Quality of Ibn Battuta Dam (Tangier, Morocco). In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML, ISBN 978-989-758-559-3, pages 350-354. DOI: 10.5220/0010734100003101

in Bibtex Style

@conference{bml21,
author={El Mustapha Azzirgue and Farida Salmoun and El Khalil Cherif and Taha Ait Tchakoucht and Nezha Mejjad},
title={Using Machine Learning Approaches to Predict Water Quality of Ibn Battuta Dam (Tangier, Morocco)},
booktitle={Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,},
year={2021},
pages={350-354},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010734100003101},
isbn={978-989-758-559-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,
TI - Using Machine Learning Approaches to Predict Water Quality of Ibn Battuta Dam (Tangier, Morocco)
SN - 978-989-758-559-3
AU - Azzirgue E.
AU - Salmoun F.
AU - Cherif E.
AU - Ait Tchakoucht T.
AU - Mejjad N.
PY - 2021
SP - 350
EP - 354
DO - 10.5220/0010734100003101