Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass Distribution for Deep Learning Biomass Estimation
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors found that traditional ways of estimating tree biomass using fixed plots can have errors, especially for small areas due to edge effects. They tested a new method that uses detailed continuous maps of biomass (called Horizontal Biomass Distribution) from 3D models of forests. Their new method improved accuracy, especially for small plot sizes, by reducing those edge-related errors. This shows that using continuous biomass mapping can make small-scale biomass estimates more reliable.
LiDARAbove-ground biomassQuantitative Structure Models3D U-NetForest inventoryEdge effectsHorizontal Biomass DistributionRelative Root Mean Square ErrorPlot-level aggregates
Authors
Nils Griese, Christoph Kleinn, Nils Nölke
Abstract
Conventional modeling approaches for LiDAR-based above-ground biomass (AGB) estimation rely on discrete plot-level inventory aggregates. This methodology introduces boundary-effect uncertainties that may severely degrade model performance within small field plots. To solve this limitation, we evaluate a Horizontal Biomass Distribution (HBD) reference mapped continuously from Quantitative Structure Models (QSMs). We trained a sparse 3D U-Net on simulated broadleaved forest structures using three AGB reference types: a standard forest inventory (FI) plot-level aggregate, an edge-effect-free QSM plot-level aggregate, and a continuous HBD mapping. Evaluating training plot sizes scaling from 100 to 2500 $m^2$ , QSM-based models systematically outperformed FI approaches at small plot sizes. Specifically, for 100 $m^2$ plots, the HBD reference reduced the relative root mean square error (RRMSE) by 16.84 $\pm$ 4.37 % and increased $R^2$ by 0.22 $\pm$ 0.05 against the FI baseline. By replacing plot level aggregates with HBDs as AGB reference, this methodology corrects for edge-effects and shows that using an HBD-based reference enhances model performance for small plot sizes.