Uncertainty Assessment in Deep Learning-based Plant Trait Retrievals from Hyperspectral data

作者：Eya Cherif, Teja Kattenborn, Luke A. Brown, Michael Ewald, Katja Berger, Phuong D. Dao, Tobias Hank, Étienne Laliberté, Bing Lu, Hannes Feilhauer · 发表于：Biogeosciences · 年份：2026 · DOI：10.5194/bg-23-2235-2026 · 被引用次数：2 · 研究领域：Spectroscopy and Chemometric Analyses

Abstract. Large-scale mapping of plant biophysical and biochemical traits is essential for ecological and environmental applications. Given their finer spectral resolution and unprecedented data availability, hyperspectral data, in concert with machine and particularly deep learning models, have emerged as a promising, non-destructive tool for accurately retrieving these traits. However, when deploying these methods on a large scale, reliably quantifying the associated uncertainty remains a critical challenge, especially when models encounter out-of-domain (OOD) data, i.e., samples that differ substantially from those of the training data, such as unseen geographical regions, species, biomes, data acquisition modalities, or scene components (e.g., clouds and water bodies). Traditional uncertainty quantification methods for deep learning models, including deep ensembles (deterministic and probabilistic) and Monte Carlo dropout, rely on the variance of predictions but often fail to capture uncertainty in OOD scenarios, leading to overly optimistic and possibly misleading uncertainty estimates. To address this limitation, we propose a distance-based uncertainty estimation method (Dis_UN) that quantifies prediction uncertainty by measuring the dissimilarity in the predictor space (spectral inputs) and embedding space (features learned by the deep model) between the training and test data. Dis_UN leverages residuals as a proxy for uncertainty and employs dissimilarity indices in d...