Dataset and Codes associated with the article “Dry or humid? Modeling drought dynamics in North African semi-arid forests using machine learning, deep learning, and stochastic approaches”

Description of the datasetThis dataset is associated with the article “Dry or humid? Modeling drought dynamics in North African semi-arid forests using machine learning, deep learning, and stochastic approaches.” It provides openly accessible monthly climatic data for three representative forest ecosystems in northeastern Algeria: Yabous, Messara, and El Hamma, covering the period 1993–2023 (31 years). The Excel file is organized into five sheets containing monthly averages of key climatic variables: precipitation (mm), mean temperature (°C), minimum temperature (°C), maximum temperature (°C), and wind speed (m/s).MethodsClimatic data were obtained from the Climate Engine platform (https://www.climateengine.org/) and aggregated at the monthly scale to ensure consistency with drought index calculations. These variables represent primary drivers of drought dynamics in semi-arid forest ecosystems. The dataset is intended to support reproducibility of analyses in the associated article and may serve as a baseline for future studies on drought monitoring, climate variability, and ecosystem resilience in North Africa.File formatExcel file (.xlsx) with five sheets corresponding to each climatic variable.