<p>Morocco’s oases, critical agroecological systems in arid regions, face escalating water scarcity due to climate variability, groundwater depletion, and a historic decline in palm groves from 15 million to 4 million trees over the past century. This study introduces a machine learning (ML)-based precipitation forecasting framework to enhance water resource management in four semi-arid Moroccan regions: Errachidia, Figuig, Tata, and Zagora. Leveraging a 1981–2025 dekadal rainfall dataset from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS v2), we developed and compared four ML models: XGBoost, CatBoost, Long Short-Term Memory (LSTM), and Temporal Convolutional Network (TCN). CatBoost emerged as the most effective, achieving a testing <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="704_2025_5677_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="24" /> </InlineMediaObject> <EquationSource Format="TEX">\(\varvec{R^2}\)</EquationSource> </InlineEquation> of 0.9818 and a mean squared error (MSE) of 0.5430 mm<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="704_2025_5677_Article_IEq2.gif" Format="GIF" Height="10" Rendition="HTML" Resolution="72" Type="Linedraw" Width="8" /> </InlineMediaObject> <EquationSource Format="TEX">\(^2\)</EquationSource> </InlineEquation> on historical data (2019–2025), and a fine-tuned 90-day forecast (March 5–June 3, 2025) with <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="704_2025_5677_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="24" /> </InlineMediaObject> <EquationSource Format="TEX">\(\varvec{R^2}\)</EquationSource> </InlineEquation> of <InlineEquation ID="IEq4"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="704_2025_5677_Article_IEq4.gif" Format="GIF" Height="15" Rendition="HTML" Resolution="72" Type="Linedraw" Width="114" /> </InlineMediaObject> <EquationSource Format="TEX">\(\varvec{0.985 \pm 0.002}\)</EquationSource> </InlineEquation> and MSE of 0.3364 mm<InlineEquation ID="IEq5"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="704_2025_5677_Article_IEq2.gif" Format="GIF" Height="10" Rendition="HTML" Resolution="72" Type="Linedraw" Width="8" /> </InlineMediaObject> <EquationSource Format="TEX">\(^2\)</EquationSource> </InlineEquation>. Historical trends revealed declining precipitation post-2015, underscoring the need for predictive tools. These findings demonstrate CatBoost’s superior ability to capture nonlinear rainfall dynamics, offering a scalable solution for climate-resilient water management in water-scarce regions. However, challenges such as data sparsity and model interpretability highlight the need for enhanced observational networks and explainable AI approaches to maximize practical adoption.</p>

Forecasting short-term rainfall patterns in arid and semi-arid regions using machine learning and deep learning models: a case study from Morocco

期刊论文
发表日期：

2025年7月29日

查看全文

Abdessamad Elmotawakkil,
Adil Moumane,
Abdelkhalik Sadiki,
Assia Zahi,
Jamal Al Karkouri,
Mouhcine Batchi,
Suraj Kumar Bhagat,
Nourddine Enneya

摘要

Morocco’s oases, critical agroecological systems in arid regions, face escalating water scarcity due to climate variability, groundwater depletion, and a historic decline in palm groves from 15 million to 4 million trees over the past century. This study introduces a machine learning (ML)-based precipitation forecasting framework to enhance water resource management in four semi-arid Moroccan regions: Errachidia, Figuig, Tata, and Zagora. Leveraging a 1981–2025 dekadal rainfall dataset from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS v2), we developed and compared four ML models: XGBoost, CatBoost, Long Short-Term Memory (LSTM), and Temporal Convolutional Network (TCN). CatBoost emerged as the most effective, achieving a testing \(\varvec{R^2}\) of 0.9818 and a mean squared error (MSE) of 0.5430 mm \(^2\) on historical data (2019–2025), and a fine-tuned 90-day forecast (March 5–June 3, 2025) with \(\varvec{R^2}\) of \(\varvec{0.985 \pm 0.002}\) and MSE of 0.3364 mm \(^2\) . Historical trends revealed declining precipitation post-2015, underscoring the need for predictive tools. These findings demonstrate CatBoost’s superior ability to capture nonlinear rainfall dynamics, offering a scalable solution for climate-resilient water management in water-scarce regions. However, challenges such as data sparsity and model interpretability highlight the need for enhanced observational networks and explainable AI approaches to maximize practical adoption.