Benchmarking Earth Observation Embeddings for Pan-EU Aboveground Biomass Mapping

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.

Authors

Institutions

Publication Details

Published
2026-11-17
DOI
https://doi.org/10.5194/egusphere-2026-6643
Primary Topic
Remote Sensing and LiDAR Applications
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Benchmarking Earth Observation Embeddings for Pan-EU Aboveground Biomass Mapping

Tomislav Hengl A, Yu-Feng Ho, Leandro Parente, Madlene Nussbaum et al.
1 links
Remote Sensing and LiDAR Applications
preprint

Benchmarking Earth Observation Embeddings for Pan-EU Aboveground Biomass Mapping

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

Abstract

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.

University of Groningen (NL), Utrecht University (NL), Dialyse Centrum Groningen (NL), GFZ Helmholtz Centre for Geosciences (DE)
HORIZON EUROPE Framework Programme, Helmholtz-Zentrum Potsdam - Deutsches GeoForschungsZentrum GFZ
Life on land, Climate action
Remote Sensing and LiDAR Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon