Improving Forest Baseline Maps in Tropical Wetlands Using GEDI-Based Forest Height Information and Sentinel-1

Abstract

Remote Sensing-based global Forest/Non-Forest (FNF) masks have shown large inaccuracies in tropical wetland areas. This limits their applications for deforestation monitoring and alerting in which they are used as a baseline for mapping new deforestation. In radar-based deforestation monitoring, for example, moisture dynamics in unmasked non-forest areas can lead to false detections. We combined a GEDI Forest Height product and Sentinel-1 radar data to improve FNF masks in wetland areas in Gabon using a Random Forest model. The GEDI Forest Height, together with texture metrics derived from Sentinel-1 mean backscatter values, were the most important contributors to the classification. Quantitatively, our mask outperformed existing global FNF masks by increasing the Producer’s Accuracy for the non-forest class by 14%. The GEDI Forest Height product by itself also showed high accuracies but contained Landsat artifacts. Qualitatively, our model was best able to cleanly uncover non-forest areas and mitigate the impact of Landsat artifacts in the GEDI Forest Height product. An advantage of the methodology presented here is that it can be adapted for different application needs by varying the probability threshold of the Random Forest output. This study stresses that, in any application of the suggested methodology, it is important to consider the UA/PA trade-off and the effect it has on the classification. The targeted improvements for wetland forest mapping presented in this paper can help raise the accuracy of tropical deforestation monitoring.

Monitoring Cropland Abandonment in Hilly Areas with Sentinel-1 and Sentinel-2 Timeseries

“…For a wider range of monitoring and mapping needs, Adugna Mullissa et al [37,38] upgraded the preprocessing framework on GEE, including additional border noise correction, speckle filtering, and radiometric terrain normalization. The framework has been successfully used in the studies of land use and land cover [39,40].…”

Impact of Ecological Water Transfer Project on Vegetation Recovery in Dried-Up Kongque River, Northwest China

“…In this study, the NDVI inverted from optical satellite data was mainly used to obtain the greenness and health status of vegetation. While compared to optical satellites, LiDAR data such as Global Ecosystem Dynamics Investigation (GEDI) and Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) offer the capability to measure the three-dimensional structure of vegetation, forests, and terrain on the Earth surface [71,72], providing information on tree height and biomass. The availability of such data can greatly enhance the precision of assessments of ecological recovery following EWTP implementation in dried-up river ecosystems.…”

Using GEDI as training data for an ongoing mapping of landscape-scale dynamics of the plant area index

“…However, previous studies that aimed at wall-to-wall mapping of GEDI-derived variables used temporally aggregation, i.e. long-term means of such variables (Healey et al 2020, Potapov et al 2020, Chen et al 2021, Dorado-Roda et al 2021, Khati et al 2021, Verhelst et al 2021, Francini et al 2022, Shendryk 2022. This is certainly suitable for a detection of large-scale spatial patterns, however, does not support seasonality and is hence not suitable for studies that require the consideration of phenology.…”