Preprints
https://doi.org/10.5194/egusphere-2026-6643
https://doi.org/10.5194/egusphere-2026-6643
17 Nov 2026
 | 17 Nov 2026
Status: this preprint is open for discussion and under review for Earth Observation (EO).

Benchmarking Earth Observation Embeddings for Pan-EU Aboveground Biomass Mapping

Yu-Feng Ho, Madlene Nussbaum, Léa Enguehard, Qian Song, Mustafa Serkan Isik, Jordy de Lange, Carmelo Bonannella, Leandro Parente, Derek Karssenberg, Martin Herold, Ichsani Wheeler, and Tomislav Hengl

Abstract. The paper presents a comprehensive evaluation of pre-trained Earth Observation (EO) embeddings compared to traditional remote sensing approaches trained with standard multi-sensor satellite data (Sentinel-1, Sentinel-2, and ALOS PALSAR-2, both with and without the addition of multi-scale terrain derivatives) for mapping aboveground biomass density (AGBD). The rank result was evaluated on 4 criteria: point-estimate accuracy, spatial pattern reconstruction, saturation effects, and uncertainty quantification. EO features were specifically used with tree-based (Quantile Random Forest Regression; QRFR) and deep learning (Convolutional Neural Network; CNN) models to map AGBD across varied biogeographical region in Finland (≈ 73,000 km2), Spain (≈ 273,000 km2), and the Netherlands (≈ 2,200 km2). A proportional stratified sampling design using airborne laser scanning (ALS) estimates of AGBD was implemented to generate sample tiles for each country, and country-specific models were trained. The benchmarking results show that EO embeddings achieve predictive accuracy that is highly competitive when compared with models that use Sentinel-1, Sentinel-2, and PALSAR: the lowest RMSE values were recorded by AlphaEarth – QRFR with terrain variables in the Netherlands (42.1 Mg ha−1), SpheerFM – CNN in Spain (17.5 Mg ha−1), and TESSERA – CNN in Finland (13.4 Mg ha−1). Pairing these embeddings with a CNN model yielded clear performance gains: TESSERA improved across all three test countries, while SpheerFM showed distinct enhancements in Spain and Finland. This strong performance was further corroborated by spatial pattern reconstruction metrics. In addition, a rigorous uncertainty assessment of both the QRFR and CNN models using empirical metrics, Prediction Interval Coverage Probability (PICP) and Mean Prediction Interval (MPI), showed that both models derive unbiased, well-calibrated prediction intervals. Ultimately, TESSERA utilized CNN as downstream model comes as the highest-ranked configuration. The result from different predictors set is also marginal, implying no single set dominates. The choice of applying EO embeddings for large-scale AGBD mapping requires consideration also data licensing and transparency, data volume, and their existing spatial temporal coverage.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Yu-Feng Ho, Madlene Nussbaum, Léa Enguehard, Qian Song, Mustafa Serkan Isik, Jordy de Lange, Carmelo Bonannella, Leandro Parente, Derek Karssenberg, Martin Herold, Ichsani Wheeler, and Tomislav Hengl

Status: open (until 29 Dec 2026)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Yu-Feng Ho, Madlene Nussbaum, Léa Enguehard, Qian Song, Mustafa Serkan Isik, Jordy de Lange, Carmelo Bonannella, Leandro Parente, Derek Karssenberg, Martin Herold, Ichsani Wheeler, and Tomislav Hengl
Yu-Feng Ho, Madlene Nussbaum, Léa Enguehard, Qian Song, Mustafa Serkan Isik, Jordy de Lange, Carmelo Bonannella, Leandro Parente, Derek Karssenberg, Martin Herold, Ichsani Wheeler, and Tomislav Hengl
Metrics will be available soon.
Latest update: 18 Nov 2026
Download
Short summary
This study presents a comprehensive machine learning benchmark for estimating aboveground biomass density (AGBD). Moving beyond standard prediction errors, we uniquely evaluate models across other three dimensions: spatial pattern reconstruction, uncertainty, and saturation effects. Our findings demonstrate that Earth observation embeddings are highly effective AGBD predictors, while Convolutional Neural Networks significantly improve spatial map reconstruction.
Share