From Noisy Historical Maps to Time-Series Oil Palm Mapping Without Annotation in Malaysia and Indonesia (2020-2024)

TL;DR

This study develops a deep learning method to produce high-resolution, time-series oil palm maps in Southeast Asia using Sentinel-2 data, without manual annotation, to aid environmental monitoring.

Contribution

It introduces a novel U-Net based framework with DMI to effectively handle label noise and generate accurate plantation maps from coarse historical labels.

Findings

Oil palm coverage peaked in 2022 and declined in 2024.

The method achieved over 70% accuracy in 2020.

Land cover analysis shows expansion into flooded areas.

Abstract

Accurate monitoring of oil palm plantations is critical 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-meter 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-meter historical labels and 10-meter 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 2,058 manually verified points, achieving overall accuracies of 70.64%, 63.53%, and 60.06% for the years 2020, 2022, and 2024, respectively. Our comprehensive analysis reveals that oil palm coverage in the region peaked in 2022 before experiencing a decline in 2024. Furthermore, land cover transition analysis highlights a concerning trajectory of plantation expansion into flooded vegetation areas, despite a general stabilization in rotations with other crop types. These high-resolution maps provide essential data for monitoring sustainability commitments and deforestation dynamics in the region, and the generated datasets are made publicly available at https://doi.org/10.5281/zenodo.17768444.