Toward 10 m Regional-Scale Time-Series Oil Palm Mapping in Malaysia and Indonesia (2020–2024) Using Sentinel-2 and Noise-Robust Deep Learning from Low-Resolution Historical Maps

Accurate monitoring of oil palm plantations is important for balancing economic development with environmental conservation in Southeast Asia. However, existing plantation maps often suffer from low spatial resolution and a lack of recent temporal coverage, impeding effective surveillance of rapid land-use changes. In this study, we propose a deep learning framework to generate 10 m resolution oil palm plantation maps for Indonesia and Malaysia from 2020 to 2024, utilizing Sentinel-2 imagery without requiring new manual annotations. To address the resolution mismatch between coarse 100 m historical labels and 10 m imagery, we employ a U-Net architecture optimized with Determinant-based Mutual Information (DMI). This approach effectively mitigates the influence of label noise. We validated our method against 2058 manually verified points, achieving overall accuracies of 70.64%, 63.53%, and 60.06% for the years 2020, 2022, and 2024, respectively. The gradual decline in accuracy with time is consistent with a growing temporal mismatch between the 2016 historical reference labels and the later prediction years. At the regional scale, the mapped oil palm area suggests a peak in 2022 followed by a lower mapped extent in 2024. Land cover transition analysis further indicates exchanges with cropland and flooded vegetation, which should be interpreted together with the reported accuracy and uncertainty. Given the moderate per-year accuracies and the temporal mismatch between the 2016 supervision and the later prediction years, these results should be interpreted as regional-scale indicators rather than pixel-level change maps. The generated maps can support regional monitoring, sustainability assessment, and prioritization of areas for further validation.