5 CONCLUSIONS
The purpose of this study was to assess whether the
two machine learning models are efficient in
predicting the quality of Ibn Batouta dam water and
to identify key water parameters allowing rapid and
accurate monitoring of water quality (K. Chen et al.
2020) (M. Najafzadeh et al. 2020). Dam water quality
prediction performance was comprehensively
compared, and potential key water parameters were
also defined and validated. Through this work, the
main conclusions are:
1. LSTM performs better than MLP in each
measurement because it is able to memorize
longtime steps, which can accurately predict long
durations.
2. The key parameters of water (Dissolved Oxygen)
have been identified and validated by the two
learning models MLP and LSTM.
3. Enriching the dataset with more experimental data
can help in tuning the applied models and thus
increasing the forecasting accuracy
4. Machine learning is recommended for future
monitoring of dam water quality, as it could
provide timely and accurate environmental alerts
and further increase the efficiency of forecasting
and decrease the cost of the dam forecast in the
future monitoring of water quality.
ACKNOWLEDGEMENTS
The authors would like to thank all the collaborators
within this work, from the Field sampling, laboratory
analysis and writing manuscript team. El Khalil
Cherif supported by FCT with the LARSyS - FCT
Project UIDB/50009/2020 and by FCT project
VOAMAIS (PTDC/EEI-AUT/31172/2017,
02/SAICT/2017/31172)
REFERENCES
Ali El Bilali et al. 2021. Groundwater quality forecasting
using machine learning algorithms for irrigation
purposes Agricultural Water Management Volume 245,
February 28 2021, 106625 https://doi.org/10.1016/
j.agwat.2020.106625
Amir Mosavi Water 2018Flood Prediction Using Machine
Learning Models: Literature Review, 10, 1536;
doi:10.3390/w10111536 www.mdpi.com/journal/
water
Azzirgue E-M, and Salmoun F, 2019. Assessment of the
Physico-Chemical Quality of Water of Oued Ouljat
Echatt and Dam Ibn Batouta-Tangier. International
Journal of Advances in Scientific Research and
Engineering (ijasre). E-ISSN: 2454-8006. Volume 5,
Issue 10 October – 2019.
Costabile, P.; Costanzo, C.; Macchione, F. A storm event
watershed model for surface runoff based on 2D fully
dynamic wave equations. Hydrol. Process. 2013, 27,
554–569.
Fernández-Pato, J.; Caviedes-Voullième, D.;
GarcíaNavarro, P. Rainfall/runoff simulation with 2D
full shallow-water equations: Sensitivity analysis and
calibration of infiltration parameters. J. Hydrol. 2016,
536, 496–513.
Hochreiter, S., Schmidhuber, J., 1997. Long short-term
memory. Neural Computation 9 (8): 1735–1780.
K. Chen et al. 2020 Comparative analysis of surface water
quality prediction performance and identification of
key water parameters using different machine learning
models based on big data / Water Research 171 (2020)
115454
Marius, P., Balas, V. E., Perescu-Popescu, L., Mastorakis,
N. E. 2009. Multilayer perceptron and neural networks.
WSEAS Transactions on Circuits and Systems 8(7).
Mohamed ACHMIT et al. 2017. Study of the
physicochemical and bacteriological quality of waters
of dam BAB LOUTA. International Journal of
Innovation and Applied Studies ISSN 2028-9324 Vol.
20 No. Jul 4 . 2017, pp. 1246-1255.
M. Najafzadeh et al. 2020. Prediction of the five-day
biochemical oxygen demand and chemical oxygen
demand in natural streams using machine learning
methods. Environ Monit Assess (2019) 191: 380
https://doi.org/10.1007/s10661-019-7446-8
Ouhmidou et al. 2015 Study of the physicochemical and
bacteriological quality of the barrage Hassan Addakhil
of Errachidia (Morocco) J. Mater. Environ. Sci. 6 (6)
(2015) 1663-1671 ISSN: 2028-2508 CODEN:
JMESCN
SETRAGEC 2018. EIE de l’AEP de la ville de Tanger et sa
région à partir du barrage Ibn Battouta –conduite eau
brute https://esa.afdb.org/sites/default/files/
EIE%20MHARHAR-AEP%20Tanger.compressed.pdf
S. Jannicke Moe et al. 2019. Predicting Lake Quality for the
Next Generation: Impacts of Catchment Management
and Climatic Factors in a Probabilistic Model
Framework. Water 2019, 11, 1767; doi:10.3390/
w11091767, www.mdpi.com/journal/water
Umair Ahmed et al. 2019. Efficient Water Quality
Prediction Using Supervised Machine Learning. Water
2019, 11, 2210; DOI: 10.3390/w11112210
www.mdpi.com/journal/water