Refined fine-scale mapping of tree cover using time series of Planet-NICFI and Sentinel-1 imagery for Southeast Asia (2016–2021)

Abstract

Abstract. High-resolution mapping of tree cover is indispensable for effectively addressing tropical forest carbon loss, climate warming, biodiversity conservation and sustainable development. However, the availability of precise, high-resolution tree cover map products remains inadequate due to the inherent limitations of mapping techniques utilizing medium- to coarse-resolution satellite imagery, such as Landsat and Sentinel-2 imagery. In this study, we have generated an annual tree cover map product at a resolution of 4.77 m for Southeast Asia (SEA) for the years 2016–2021 by integrating Norway's International Climate and Forests Initiative imagery from Planet (hereafter Planet-NICFI) and Sentinel-1 synthetic aperture radar data. We have also collected annual tree cover/non-tree cover samples to assess the accuracy of our Planet-NICFI tree cover map product. The results show that our Planet-NICFI tree cover map product for 2016–2021 achieves high accuracy, with an overall accuracy of ≥0.867 ± 0.017 and a mean F1 score of 0.921. Furthermore, our tree cover map product exhibits high temporal consistency from 2016 to 2021. Compared with existing map products (e.g., Finer Resolution Observation and Monitoring of Global Land Cover 10 m, FROM-GLC10, and European Space Agency WorldCover 2020 and 2021), our tree cover map product exhibits better performance, both statistically and visually. However, the imagery obtained from Planet-NICFI does not perform as well with respect to mapping tree cover in areas with diverse vegetation or complex landscapes due to insufficient spectral information. Nevertheless, we highlight the capability of Planet-NICFI imagery to provide quick and fine-scale tree cover mapping to a large extent. The consistent characterization of tree cover dynamics in SEA's tropical forests can be further applied in various disciplines. Our data from 2016 to 2021 at a 4.77 m resolution are publicly available at https://doi.org/10.57760/sciencedb.07173 (Yang and Zeng, 2023).