Publications
Research Publications
Forest disturbances intensify land surface warming across Europe
Y. Su, Y. Xu, X. Zhang, and 18 more authors
2026ABS Forests are vital for the carbon sequestration, biodiversity conservation, and climate regulation, making the precise and continuous monitoring of forest structure attributes such as canopy height essential. Here we present a two decades long (2004–2024), 30 m resolution annual canopy height dataset for Italy, developed using a time-series deep learning framework that integrates Landsat optical imagery with LiDAR observations. DOI CONTACT×
Substantial contribution of trees outside forests to above-ground carbon across China
Y. Su, T. Shi, X. Zhang, and 14 more authors
Communications Earth & Environment 2026ABS Accurately quantifying canopy height and above-ground carbon across diverse land-cover types is crucial for understanding carbon storage dynamics and guiding climate-mitigation strategies. Yet existing maps often overlook non-forest ecosystems. Here we present a deep learning framework based on a U-Net architecture that combines radar, optical, elevation and slope data to produce a 10 m canopy height map across China.x DOI CONTACT×
SERA-H: Beyond Native Sentinel Spatial Limits for High-Resolution Canopy Height Mapping
T. Boudras, M. Schwartz, R. Fensholt, and 6 more authors
Preprint arXiv preprint 2026ABS High-resolution mapping of canopy height is essential for forest management and biodiversity monitoring. Although recent studies have led to the advent of deep learning methods using satellite imagery to predict height maps, these approaches often face a trade-off between data accessibility and spatial resolution. To overcome these limitations, we present SERA-H, an end-to-end model combining a super-resolution module (EDSR) and temporal attention encoding (UTAE). CONTACT×
Canopy Tree Height Estimation using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing
K. Schrödter, J. Pauls, F. Gieseke
Proceedings of the 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS) 2026×
A fused canopy height map of Italy (2004–2024) from spaceborne and airborne LiDAR, and Landsat via deep learning and Bayesian averaging
Y. Su, N. Besic, X. Zhang, and 13 more authors
2025ABS Forests are vital for the carbon sequestration, biodiversity conservation, and climate regulation, making the precise and continuous monitoring of forest structure attributes such as canopy height essential. Here we present a two decades long (2004–2024), 30 m resolution annual canopy height dataset for Italy, developed using a time-series deep learning framework that integrates Landsat optical imagery with LiDAR observations. DOI CONTACT×
×
Canopy height and biomass distribution across the forests of Iberian Peninsula
Y. Su, M. Schwartz, I. Fayad, and 12 more authors
Scientific Data 2025ABS Accurate mapping of vegetation canopy height and biomass distribution is essential for effective forest monitoring, climate change mitigation, and sustainable forestry. Here we present high-resolution remote sensing-based canopy height (10 m resolution) and above ground biomass (AGB, 50 m resolution) maps for the forests of the Iberian Peninsula from 2017 to 2021, using a deep learning framework that integrates Sentinel-1, Sentinel-2, and LiDAR data. Two UNET models were developed... DOI CONTACT×
Remote-sensing-based forest canopy height mapping: some models are useful, but might they provide us with even more insights when combined?
N. Besic, N. Picard, C. Vega, and 10 more authors
Geoscientific Model Development 2025ABS The development of high-resolution mapping models for forest attributes based on remote sensing data combined with machine or deep learning techniques has become a prominent topic in the field of forest observation and monitoring. This has resulted in the availability of multiple, sometimes conflicting, sources of information, but, at face value, it also makes it possible to learn about forest attribute uncertainty through the joint interpretation of multiple models. This article seeks to endorse the latter by ... DOI CONTACT×
Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation
J. Pauls, M. Zimmer, B. Turan, and 4 more authors
Preprint arXiv preprint 2025ABS With the rise in global greenhouse gas emissions, accurate large-scale tree canopy height maps are essential for understanding forest structure, estimating above-ground biomass, and monitoring ecological disruptions. To this end, we present a novel approach to generate large-scale, high-resolution canopy height maps over time. PDF CONTACT×
DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
I. Fayad, M. Zimmer, M. Schwartz, and 6 more authors
Preprint arXiv preprint 2025ABS Significant efforts have been directed towards adapting self-supervised multimodal learning for Earth observation applications. However, most current methods produce coarse patch-sized embeddings, limiting their effectiveness and integration with other modalities like LiDAR. To close this gap, we present DUNIA, an approach to learn pixel-sized embeddings through PDF CONTACT×
SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale
M. Zimmer, C. Roux, M. Wagner, and 2 more authors
Preprint arXiv preprint 2025ABS The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often prohibitive and classical approaches such as magnitude pruning are suboptimal on Transformers. DOI CONTACT×
Compression-aware Training of Neural Networks using Frank-Wolfe
M. Zimmer, C. Spiegel, S. Pokutta
Mathematical Optimization for Machine Learning 2025ABS Many existing neural network pruning approaches rely on either retraining or inducing a strong bias in order to converge to a sparse solution throughout training. A third paradigm, compression-aware training, aims to obtain state-of-the-art dense models that are robust to a wide range of compression ratios using a single dense training run while also avoiding retraining. DOI CONTACT×
High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach
M. Schwartz, P. Ciais, C. Ottlé, and 11 more authors
International Journal of Applied Earth Observation and Geoinformation 2024ABS In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10–––20 m) is needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-sensor remote sensing measurements to create a high-resolution canopy height map over the “Landes de Gascogne” forest in France, a large maritime pine plantation of 13,000 km2 with flat terrain and intensive management. DOI CONTACT×
×
Estimating canopy height at scale
J. Pauls, M. Zimmer, U. Kelly, and 6 more authors
Preprint arXiv preprint 2024ABS We propose a framework for global-scale canopy height estimation based on satellite data. Our model leverages advanced data preprocessing techniques, resorts to a novel loss function designed to counter geolocation inaccuracies inherent in the ground-truth height measurements, and employs data from the Shuttle Radar Topography Mission to effectively filter out erroneous labels in mountainous regions, enhancing the reliability of our predictions in those areas. PDF CONTACT×
The European Forest Disturbance Atlas: a forest disturbance monitoring system using the Landsat archive
A. Viana-Soto, C. Senf, J. Sebald, R. Seidl
Earth System Science Data Discussions 2024ABS Forests in Europe are undergoing complex changes that require a comprehensive monitoring of disturbance occurrence. Here, we present the European Forest Disturbance Atlas (EFDA), a Landsat-based approach for mapping annual forest disturbances across continental Europe from 1985 onwards. PDF CONTACT×
FORMS: Forest Multiple Source height, wood volume, and biomass maps in France at 10 to 30 m resolution based on Sentinel-1, Sentinel-2, and Global Ecosystem Dynamics Investigation (GEDI) data with a deep learning approach
M. Schwartz, P. Ciais, A. De Truchis, and 9 more authors
Earth System Science Data 2023ABS The contribution of forests to carbon storage and biodiversity conservation highlights the need for accurate forest height and biomass mapping and monitoring. In France, forests are managed mainly by private owners and divided into small stands, requiring 10 to 50m spatial resolution data to be correctly separated. Further, 35% of the French forest territory is covered by mountains and Mediterranean forests which are managed very extensively. DOI CONTACT×
Quantifying post-fire shifts in woody-vegetation cover composition in Mediterranean pine forests using Landsat time series and regression-based unmixing
A. Viana-Soto, A. Okujeni, D. Pflugmacher, and 3 more authors
Remote Sensing of Environment 2022×