Spatial Domain Mismatch Between Field Plots and GEDI Inflates Aboveground Biomass Model Accuracy in a Sudanian Savanna Woodland

Abstract

Accurate estimation of aboveground biomass (AGB) in dryland savanna woodlands is constrained by sparse field data, which has motivated widespread fusion of field plots with spaceborne LiDAR reference data from the Global Ecosystem Dynamics Investigation (GEDI). Here, we show that such fusion can substantially inflate apparent model accuracy when the two reference sources sample different spatial domains. Using 44 field plots from the Abu-Gadaf Natural Reserved Forest (AGNRF), Sudan, and 56 GEDI L4A footprints drawn from a 50 km buffer surrounding the reserve, we trained Random Forest (RF), Gradient Boosting (GB) and Classification and Regression Tree (CART) models on Sentinel-1, Sentinel-2, SRTM and Dynamic World predictors and evaluated them under 10-fold, 2 km block spatial cross-validation. The merged dataset yielded apparently moderate performance (RF: RMSE = 9.40 Mg ha−1, R2 = 0.33). However, GEDI-derived AGB was 2.1 times higher than field-measured AGB (18.71 vs. 8.89 Mg ha−1; Kolmogorov–Smirnov D = 0.53, p

Code and data availability

The supplied blocks describe field plots, GEDI L4A footprints, and GEE/R-based analysis, but contain no public deposit of the paper's phenotype data, imagery, code, or models. Google Earth Engine is cited only as a generic processing platform, and no availability statement or authors' URL for paper-specific assets is给定

No evidence-backed public reproduction asset is currently recorded.