Phenology-Informed Crop Type Mapping in Semi-Arid Morocco Using Sentinel-2 NDVI Time Series: A Machine Learning Approach with Temporal Sensitivity Analysis

Abstract

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 (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 lowest accuracy (F1 = 0.61) due to confusion with olives. Dynamic Time Warping (DTW) analysis quantified phenological similarity between crops, 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.