Support Vector Machine (SVM) classifiers are widely used for satellite-based crop mapping, yet hyperparameter tuning is often treated as a black-box process, with limited insight into how individual parameters influence classification performance. This limitation becomes critical when deploying SVM models across heterogeneous agricultural landscapes, where robustness and transferability are required. This study systematically investigates the sensitivity of SVM hyperparameters for crop type discrimination using Sentinel-2 NDVI time series over the Al Haouz plain in central Morocco, a heterogeneous irrigated agricultural region comprising winter cereals and perennial orchards. An exhaustive grid search was conducted across multiple orders of magnitude for the regularization parameter C (0.01–1000) and the RBF kernel coefficient γ (0.001–10). Model performance was evaluated using F1-score, Recall, and Overall Accuracy for six crop classes with contrasting phenological patterns.Results reveal a pronounced asymmetry in hyperparameter influence. The regularization parameter C exhibits a high degree of robustness: once a moderate threshold is reached (C ≥ 1), classification performance stabilizes and remains insensitive to further increases. In contrast, γ shows a narrow optimal range (0.1–1.0), beyond which performance rapidly deteriorates. High γ values induce overfitting, particularly among crops with similar seasonal dynamics, as evidenced by persistent confusion between citrus and olive classes. The optimal configuration (C = 1, γ = 1) achieved an F1-score of 0.80 and an Overall Accuracy of 81%. More importantly, sensitivity analysis demonstrates that γ plays a dominant role in model calibration. These findings provide practical guidance for deploying robust SVM classifiers in data-limited agricultural contexts, where extensive hyperparameter tuning is often impractical.
In Morocco, snow constitutes a crucial freshwater resource, particularly in the Atlas Mountains, where seasonal snowpack significantly contributes to surface water availability, groundwater recharge, and down-stream water supply. However, snow monitoring in these regions remains challenging due to the scarcity and uneven distribution of ground-based snow depth measurements, especially at high altitudes. This lack of observations limits the accurate assessment of snowpack dynamics and hampers hydrological modeling and water resource management. In this study, we assessed the performance of an empirical approach to estimate snow depth from satellite-derived fractional snow cover (FSC) obtained from MODIS observations. Five empirical FSC snow depth models, including linear and nonlinear exponential formulations, are developed and applied across multiple regions of the Moroccan Atlas Mountains. Model coefficients are calibrated independently for each region using three complementary optimization techniques, nonlinear least squares regression, genetic algorithms, and simulated annealing. Model skill was evaluated during calibration and validation using the Kling–Gupta Efficiency (KGE), Pearson correlation coefficient (R), and absolute error metrics (RMSE and MAE). Results show substantial performance differences across formulations and regions. The most flexible exponential model achieved highest efficiency (KGE up to 0.87; R > 0.85) and 0.26 cm (MAE) under moderate snow conditions. Linear formulations exhibited limited robustness, whereas exponential models better captured snow depth dynamics, particularly in high-altitude areas with deep and persistent snowpacks. These results highlight the potential of FSC-based empirical modeling as a practical and operational solution for snow depth estimation in data-scarce mountainous regions of Morocco.
Accurate crop mapping is essential for food security and water resource management in semi-arid North Africa. This study evaluated four machine learning algorithms for crop classification using Sentinel-2 NDVI time series in the Al Haouz region, Morocco with a time series of 12 dates (December 2023–May 2024) using 105,869 ground reference samples. Support Vector Machine (SVM) achieved the highest performance (macro F1-score = 0.80, Overall Accuracy = 81%), followed by XGBoost (0.79), Random Forest (0.79), and Decision Tree (0.71). Class-wise analysis revealed excellent discrimination for apricots (F1 = 0.99) due to distinctive spring phenology, while citrus showed the lowest accuracy (F1 = 0.61) due to confusion with olives. Dynamic Time Warping (DTW) analysis quantified phenological similarity between crops, revealing that classification confusion correlates with profile similarity. Temporal sensitivity analysis revealed that reducing acquisitions from 12 to 8 dates results in only 2.4% performance loss, offering significant operational advantages for resource-limited contexts. February–March acquisitions proved most discriminative, coinciding with peak vegetative differentiation. These findings provide practical recommendations for operational crop monitoring in semi-arid African regions facing water scarcity and food security challenges.
Improving olive yield in Moroccan agro-ecosystems requires a better understanding of the interactions between water availability, soil properties, and management practices. The complexity and non-linear nature of these interactions limit the effectiveness of conventional analytical approaches. This study applies machine learning methods to predict olive yield and to assess how the importance of yield determinants varies under contrasting water regimes. A multi-site dataset from Moroccan olive groves, including more than 2,000 observations, was analyzed. Machine learning models showed high predictive accuracy across water regimes. Under rainfed conditions, CatBoost achieved the best performance (R² = 0.845), indicating that yield variability is mainly driven by soil properties and spatial context. Under irrigated conditions, XGBoost provided the highest accuracy (R² = 0.855), highlighting the increasing role of management practices such as planting density and nitrogen fertilization. Under intensive irrigation, fruit-related variables, particularly 100-fruit weight, became the dominant predictors, while the influence of edaphic constraints decreased.Overall, the results demonstrate that irrigation does not simply increase olive yield but fundamentally alters the hierarchy of factors controlling production. These findings emphasize the need for data-driven, site-specific management strategies to enhance the sustainability and efficiency of olive production in Morocco.