Groundwater is essential for sustaining water needs, industrial growth, agriculture, and ecosystems, particularly in arid regions. This study uses data from GRACE and MODIS satellites, integrating environmental variables like land surface temperature, soil moisture, terrestrial water storage, precipitation, and vegetation indices to predict groundwater levels in Morocco’s Rabat-Salé Kenitra region. These environmental variables serve as input parameters, with the output being the predicted groundwater level. Advanced machine learning models, including Gradient Boosting Regression (GBR), Support Vector Regression (SVR), Random Forest (RF), and Decision Tree (DT) were employed to capture the relationships between these variables and groundwater levels. The GBR model showed superior performance with an R2 value of 0.99, a Mean Absolute Error (MAE) of 1.94, and a Root Mean Squared Error (RMSE) of 2.98, significantly improving over traditional methods that struggle with non-linear relationships and data noise. Compared to existing methods, our approach offers enhanced accuracy and robustness due to the GBR model’s ability to handle complex and non-linear relationships. This study demonstrates the advantages of integrating diverse environmental datasets with advanced machine learning techniques, improving groundwater management strategies and prediction reliability, especially in regions facing significant water scarcity and climate change impacts.

Groundwater plays a crucial role in sustaining agriculture and livelihoods in the arid Middle Draa Valley (MDV) of southeastern Morocco. However, increasing groundwater extraction, declining rainfall, and the absence of effective floodwater harvesting systems have led to severe aquifer depletion. This study applies and compares six machine learning (ML) algorithms—decision trees (CART), ensemble methods (random forest, LightGBM, XGBoost), distance-based learning (k-nearest neighbors), and support vector machines—integrating GIS, satellite data, and field observations to delineate zones suitable for groundwater recharge. The results indicate that ensemble tree-based methods yielded the highest predictive accuracy, with LightGBM outperforming the others by achieving an overall accuracy of 0.90. Random forest and XGBoost also demonstrated strong performance, effectively identifying priority areas for artificial recharge, particularly near ephemeral streams. A feature importance analysis revealed that soil permeability, elevation, and stream proximity were the most influential variables in recharge zone delineation. The generated maps provide valuable support for irrigation planning, aquifer conservation, and floodwater management. Overall, the proposed machine learning–geospatial framework offers a robust and transferable approach for mapping groundwater recharge zones (GWRZ) in arid and semi-arid regions, contributing to the achievement of Sustainable Development Goals (SDGs))—notably SDG 6 (Clean Water and Sanitation), by enhancing water-use efficiency and groundwater recharge (Target 6.4), and SDG 13 (Climate Action), by supporting climate-resilient aquifer management.

The Rabat–Salé–Kénitra region of Morocco faces critical groundwater challenges due to increasing demands from population growth, agricultural expansion, and the impacts of prolonged droughts and climate change. This study employs advanced machine learning models, including artificial neural networks (ANN), gradient boosting (GB), support vector regression (SVR), decision tree (DT), and random forest (RF), to predict groundwater storage variations. The dataset encompasses hydrological, meteorological, and geological factors. Among the models evaluated, RF demonstrated superior performance, achieving a mean squared error (MSE) of 484.800, a root mean squared error (RMSE) of 22.018, a mean absolute error (MAE) of 14.986, and a coefficient of determination (R2) of 0.981. Sensitivity analysis revealed significant insights into how different models respond to variations in key environmental factors such as evapotranspiration and precipitation. Prophet was also integrated for its ability to handle seasonality in time-series data, further enhancing prediction reliability. The findings emphasize the urgent need to integrate advanced predictive models into groundwater management to address groundwater depletion and ensure sustainable water resources amid rising drought conditions. Policymakers can use these models to regulate extraction, promote water-saving technologies, and enhance recharge efforts, ensuring the sustainability of vital groundwater resources for future generations.

The combination of remote sensing with AI methods such as deep learning, along with tools like geographic information systems, has transformed both spatial analysis and how decisions are made in a variety of fields. In this chapter, the authors show how important these AI technologies and techniques can be for improving the accuracy of information produced by remote sensors when it comes to monitoring water resources managing them sustainably, assessing flooding risks and environmental monitoring, thus contributing to a more informed and sustainable future. Accurate identification of water bodies using satellite images is crucial for purposes such as managing water resources, the environment, urban planning, and reacting to disasters. This study evaluates the performance of three advanced deep learning models DeepLabV3+, U-Net, and FCN in the semantic segmentation when looking at water bodies in pictures taken by Sentinel-2 satellites. The three models were assessed by metrics of accuracy, recall, precision, F1score, and Dice coefficient. The best performer was U-Net: it scored highest overall.

Artificial intelligence (AI) plays a crucial role in soil moisture prediction, essential for sustainable agriculture in arid regions where water scarcity and climate variability threaten crop yields. This study introduces an AI-driven framework to forecast soil moisture across five sites in Morocco's Draa Valley (Agdz, Tagounite, Tamegroute, Tansikht, Zagora). A dataset (2003–2024) was built by integrating historical climate records with remote sensing indicators using Google Earth Engine (GEE). Six models Random Forest (RF), XGBoost, CatBoost, k-Nearest Neighbors (KNN), Long Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN) were assessed with RMSE, NSE, MSE, and MAPE. Results showed that tree-based models clearly outperformed deep learning, with RF, XGBoost, and CatBoost achieving RMSE of 2.89%–9.11% and NSE > 0.965. Findings highlight the potential of AI-based soil moisture prediction to enhance irrigation scheduling, optimize water allocation, and support climate-resilient farming, offering a scalable solution for precision agriculture.