Uncertainty-aware tree height change regression
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a detailed dataset that measures how much the height of tree canopies changes over time in parts of Spain, using satellite images. Instead of just saying whether the canopy changed or not, their data shows exactly how much it changed and how sure they are about these measurements. They also introduced new ways to teach computer models to predict these changes while accounting for uncertainty. Their work helps improve how we track forest growth and loss more accurately with advanced machine learning tools.
canopy heightremote sensingchange detectioncontinuous changeuncertainty estimationGeospatial Foundation Modelssatellite imageryPlanetScopechange regressionforest dynamics
Authors
Max Gaber, Dimitri Gominski, Jaime C. Revenga, Stefan Oehmcke, Rasmus Fensholt, Martin Brandt
Abstract
Monitoring canopy height change is essential for understanding carbon sinks and forest dynamics. Remote sensing enables consistent, large-scale observations of such changes, increasingly integrated with deep learning architectures such as Geospatial Foundation Models (GFMs). However, existing methods and datasets frame the problem as binary change detection, which overlooks both the continuous nature of change, especially for vegetation, and the inherent uncertainty in labels. We present the Canopy Height Change (CHC) dataset, providing 3 $\mathrm{m}$ resolution continuous canopy height differences and associated spatially resolved uncertainties across 10598 $\mathrm{km}^2$ of northern and western Spain. The dataset is paired with a co-located time series of PlanetScope satellite imagery. Based on the dataset, we introduce the task of uncertainty-aware change regression, associated metrics and strategies for fine-tuning GFMs. Furthermore, we evaluate state-of-the-art GFMs and highlight promising directions and remaining challenges for advancing continuous canopy height change estimation.