Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin

Morocco is geographically located between two distinct climatic zones: temperate in the north and tropical in the south. This situation is the reason for the temporal and spatial variability of the Moroccan climate. In recent years, the increasing scarcity of water resources, exacerbated by climate...

Full description

Saved in:
Bibliographic Details
Main Authors: Fatima Zehrae Elhallaoui Oueldkaddour, Fatima Wariaghli, Hassane Brirhet, Ahmed Yahyaoui, Hassane Jaziri
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Limnological Review
Subjects:
Online Access:https://www.mdpi.com/2300-7575/25/1/6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091208357969920
author Fatima Zehrae Elhallaoui Oueldkaddour
Fatima Wariaghli
Hassane Brirhet
Ahmed Yahyaoui
Hassane Jaziri
author_facet Fatima Zehrae Elhallaoui Oueldkaddour
Fatima Wariaghli
Hassane Brirhet
Ahmed Yahyaoui
Hassane Jaziri
author_sort Fatima Zehrae Elhallaoui Oueldkaddour
collection DOAJ
description Morocco is geographically located between two distinct climatic zones: temperate in the north and tropical in the south. This situation is the reason for the temporal and spatial variability of the Moroccan climate. In recent years, the increasing scarcity of water resources, exacerbated by climate change, has underscored the critical role of dams as essential water reservoirs. These dams serve multiple purposes, including flood management, hydropower generation, irrigation, and drinking water supply. Accurate estimation of reservoir flow rates is vital for effective water resource management, particularly in the context of climate variability. The prediction of monthly runoff time series is a key component of water resources planning and development projects. In this study, we employ Machine Learning (ML) techniques—specifically, Random Forest (RF), Support Vector Regression (SVR), and XGBoost—to predict monthly river flows in the Bouregreg basin, using data collected from the Sidi Mohamed Ben Abdellah (SMBA) Dam between 2010 and 2020. The primary objective of this paper is to comparatively evaluate the applicability of these three ML models for flow forecasting in the Bouregreg River. The models’ performance was assessed using three key criteria: the correlation coefficient (R<sup>2</sup>), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). The results demonstrate that the SVR model outperformed the RF and XGBoost models, achieving high accuracy in flow prediction. These findings are highly encouraging and highlight the potential of machine learning approaches for hydrological forecasting in semi-arid regions. Notably, the models used in this study are less data-intensive compared to traditional methods, addressing a significant challenge in hydrological modeling. This research opens new avenues for the application of ML techniques in water resource management and suggests that these methods could be generalized to other basins in Morocco, promoting efficient, effective, and integrated water resource management strategies.
format Article
id doaj-art-b28a87d8d6504718918f394dc5c7fc98
institution DOAJ
issn 2300-7575
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Limnological Review
spelling doaj-art-b28a87d8d6504718918f394dc5c7fc982025-08-20T02:42:25ZengMDPI AGLimnological Review2300-75752025-03-01251610.3390/limnolrev25010006Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg BasinFatima Zehrae Elhallaoui Oueldkaddour0Fatima Wariaghli1Hassane Brirhet2Ahmed Yahyaoui3Hassane Jaziri4Laboratory of Biodiversity, Ecology and Genome, Faculty of Sciences, University Mohammed V in Rabat, Rabat 10000, MoroccoLaboratory of Biodiversity, Ecology and Genome, Faculty of Sciences, University Mohammed V in Rabat, Rabat 10000, MoroccoDepartment of Water Research and Planning, Ministry of Equipment, Transport, Logistics and Water, Rabat 10000, MoroccoLaboratory of Biodiversity, Ecology and Genome, Faculty of Sciences, University Mohammed V in Rabat, Rabat 10000, MoroccoLaboratory of Biodiversity, Ecology and Genome, Faculty of Sciences, University Mohammed V in Rabat, Rabat 10000, MoroccoMorocco is geographically located between two distinct climatic zones: temperate in the north and tropical in the south. This situation is the reason for the temporal and spatial variability of the Moroccan climate. In recent years, the increasing scarcity of water resources, exacerbated by climate change, has underscored the critical role of dams as essential water reservoirs. These dams serve multiple purposes, including flood management, hydropower generation, irrigation, and drinking water supply. Accurate estimation of reservoir flow rates is vital for effective water resource management, particularly in the context of climate variability. The prediction of monthly runoff time series is a key component of water resources planning and development projects. In this study, we employ Machine Learning (ML) techniques—specifically, Random Forest (RF), Support Vector Regression (SVR), and XGBoost—to predict monthly river flows in the Bouregreg basin, using data collected from the Sidi Mohamed Ben Abdellah (SMBA) Dam between 2010 and 2020. The primary objective of this paper is to comparatively evaluate the applicability of these three ML models for flow forecasting in the Bouregreg River. The models’ performance was assessed using three key criteria: the correlation coefficient (R<sup>2</sup>), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). The results demonstrate that the SVR model outperformed the RF and XGBoost models, achieving high accuracy in flow prediction. These findings are highly encouraging and highlight the potential of machine learning approaches for hydrological forecasting in semi-arid regions. Notably, the models used in this study are less data-intensive compared to traditional methods, addressing a significant challenge in hydrological modeling. This research opens new avenues for the application of ML techniques in water resource management and suggests that these methods could be generalized to other basins in Morocco, promoting efficient, effective, and integrated water resource management strategies.https://www.mdpi.com/2300-7575/25/1/6flow forecastingtime seriesmachine learningRandom Forest modelSVR modelXGBoost model
spellingShingle Fatima Zehrae Elhallaoui Oueldkaddour
Fatima Wariaghli
Hassane Brirhet
Ahmed Yahyaoui
Hassane Jaziri
Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin
Limnological Review
flow forecasting
time series
machine learning
Random Forest model
SVR model
XGBoost model
title Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin
title_full Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin
title_fullStr Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin
title_full_unstemmed Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin
title_short Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin
title_sort comparison of machine learning models for real time flow forecasting in the semi arid bouregreg basin
topic flow forecasting
time series
machine learning
Random Forest model
SVR model
XGBoost model
url https://www.mdpi.com/2300-7575/25/1/6
work_keys_str_mv AT fatimazehraeelhallaouioueldkaddour comparisonofmachinelearningmodelsforrealtimeflowforecastinginthesemiaridbouregregbasin
AT fatimawariaghli comparisonofmachinelearningmodelsforrealtimeflowforecastinginthesemiaridbouregregbasin
AT hassanebrirhet comparisonofmachinelearningmodelsforrealtimeflowforecastinginthesemiaridbouregregbasin
AT ahmedyahyaoui comparisonofmachinelearningmodelsforrealtimeflowforecastinginthesemiaridbouregregbasin
AT hassanejaziri comparisonofmachinelearningmodelsforrealtimeflowforecastinginthesemiaridbouregregbasin