Abstract
Accurate maize distribution information is critical for crop-area statistics, food-security assessment, and agricultural monitoring, but large-scale maize-mapping remains difficult in regions with limited reference samples, heterogeneous crop calendars, and frequent optical data gaps. This study proposes a phenology-adaptive maize mapping framework based on Sentinel-2 time-series imagery and an Enhanced Red-edge NDVI (ENDVIre). ENDVIre was constructed from the Sentinel-2 red-edge 4 and red-edge 2 bands to enhance the spectral response of maize during the silking-to-grain-filling stage, when maize develops a dense canopy and high chlorophyll content but is often confused with soybean. The framework first reconstructed the NDVI time series using an upper-envelope-constrained Whittaker smoother to identify key phenological stages, including sowing–emergence, vigorous growth, and maturity–harvest. NDVI, ENDVIre, and LSWI were then integrated into an interpretable decision-tree model with phenology-aligned time windows to distinguish maize from soybean, rice, wheat, and other non-maize backgrounds. The method was evaluated in six representative maize-growing regions across the United States, Brazil, China, Kenya, and Ukraine, covering different crop calendars, field sizes, and agricultural systems. The mean overall accuracy, F1-score, and Kappa coefficient across the six regions reached 93.27%, 93.14%, and 0.8652, respectively. Cross-year experiments in a winter-wheat–summer-maize rotation region from 2020 to 2024 achieved overall accuracies of 89.80–96.80%, while spatial-transfer experiments in six independent regions achieved overall accuracies of 87.40–95.40%. A comparison with existing high-resolution maize products in the Huang-Huai-Hai Plain further showed that the proposed method better balanced omission and commission errors. These results indicate that ENDVIre-based phenology rules provide an interpretable and transferable solution for maize mapping under limited-sample conditions, although persistent cloud contamination and fragmented smallholder landscapes remain important challenges.