Publications
NIBIOs employees contribute to several hundred scientific articles and research reports every year. You can browse or search in our collection which contains references and links to these publications as well as other research and dissemination activities. The collection is continously updated with new and historical material.
2026
Authors
Michele Torresani Vítězslav Moudrý Christopher R. Hakkenberg Vojtěch Barták Duccio Rocchini Stefano Puliti Paweł Hawryło Krzysztof Stereńczak Alexander Cotrina-Sanchez Gabriele Giuseppe Antonio Satta Luca da Ros Patrick Kacic Roberto TognettiAbstract
Monitoring forests globally through the assessment of structural characteristics is indispensable in times of increasing disturbances and biodiversity loss. The recent development of a 1-meter resolution Global Canopy Height Map by Meta and the World Resources Institute (Meta/WRI CHM) offers new opportunities for large-scale forest structure analysis. However, its reliability for estimating key forest structural metrics in selected forest sites of the Italian Alps remains largely untested. In this study, we compared estimates of canopy cover, mean and maximum canopy height, tree count, and crown size computed from the Meta/WRI CHM with the corresponding metrics computed from airborne laser scanning (ALS)-based CHMs across five forested sites in Alpine ecosystems representing diverse forest structures, species compositions, and management practices. Our results show that the Meta/WRI CHM provides reliable estimates of canopy cover (R = 0.82–0.92, RMSE = 8%–15%) and, to some extent, mean canopy height (R = 0.69–0.85, RMSE = 2.2–2.9 m). However, it substantially underestimates maximum canopy height and fails to reliably estimate tree count, positions, and crown size, overestimating the number of trees by 200–750 per hectare. In addition, the quality of the evaluated metrics estimates varied with respect to topographic gradients (i.e., slope, aspect, and altitude). Our findings define clear application boundaries for the Meta/WRI CHM in Alpine forest environments: while the product can support stand-level estimates of canopy cover and mean canopy height, it remains unsuitable for estimating maximum canopy height and individual-tree-level metrics such as tree count, tree position, and crown size. Future efforts should focus on refining global CHMs to improve accuracy and expand their applicability for forest monitoring.
Authors
Simone Bianchi Cornelia Roberge Johannes Schumacher Johannes Breidenbach Kari T. Korhonen Harri MäkinenAbstract
Sustainable forest management needs growth models. Few studies have explored regional models in Fennoscandia despite similar conditions and challenges. We examined the feasibility of regional models for basal area increment of Norway spruce (Picea abies (L.) Karst.), Scots pine (Pinus sylvestris L.), and birch (Betula pendula Roth. and Betula pubescens Ehrh.). We compiled over 880,000 growth observations and estimated competition indices, climate variables, and site fertility classes by integrating data from recent National Forest Inventories (2004–2023) in Finland, Norway, and Sweden. Using Random Forest models, we identified the main growth drivers across countries (tree size, accumulated temperature sum, latitude, competition, and site fertility), with minor differences in their responses across countries. However, periodic NFI measurements could not capture the effect of additional climate variables. Using species-specific nonlinear mixed models, we demonstrated that predictive regional models can be fitted using those main drivers. Although we achieved only moderate predictive performance (Weighted Absolute Percentage Error of 45–71%, depending on the species and country), there were no residual geographical biases. The results confirm the potential of Fennoscandian growth models to address shared challenges. Future work should better account for site fertility, integrate process-based approaches for climate responses, and carry out independent validation.
Authors
Binbin Xiang Maciej Wielgosz Stefano Puliti Kamil Král Martin Krůček Azim Missarov Rasmus AstrupAbstract
The segmentation of forest LiDAR 3D point clouds, including both individual tree and semantic segmentation, is fundamental for advancing forest management and ecological research. However, current approaches often struggle with the complexity and variability of natural forest environments. We present ForestFormer3D, a new unified and end-to-end framework designed for precise individual tree and semantic segmentation. ForestFormer3D incorporates ISA-guided query point selection, a score-based block merging strategy during inference, and a one-to-many association mechanism for effective training. By combining these new components, our model achieves state-of-the-art performance for individual tree segmentation on the newly introduced FOR-instanceV2 dataset, which spans diverse forest types and regions. Additionally, ForestFormer3D generalizes well to unseen test sets (Wytham woods and LAUTx), showcasing its robustness across different forest conditions and sensor modalities. The FOR-instanceV2 dataset and the ForestFormer3D code are publicly available at https://bxiang233.github.io/FF3D/.
Authors
Anna Wöhlbrandt Anabel Onay Ute Bachmann-Gigl Wolfgang Falk Christian Temperli Samuel Aspalter Debojyoti Chakraborty Silvio Schüler Johannes Breidenbach Jonas Fridman Miriam Isaac-Renton Vladimír Šebeň Mitja Skudnik Tzvetan Zlatanov Dominik Thom Eric A. ThurmAbstract
Amid increasing temperatures and extended drought periods, forest managers require comprehensive information regarding the suitability of various tree species under changing climatic conditions. To address this need, we assembled a unique dataset spanning Europe, incorporating multiple data sources such as national forest inventories, forest management plans, and data from ICP Forests. Our database ultimately included over six million individual trees across 860,000 forest plots throughout Europe. Using this extensive dataset, we developed Species Distribution Models (SDM) for 30 and Site Index Models (SIM) for 25 European tree species, the latter limited by data availability. Both model types were used to generate predictions at a spatial resolution of 1 × 1 km for the periods 2011–2040, 2041–2070, and 2071–2100 under climate change scenarios RCP2.6, RCP4.5 and RCP8.5. The model predictions aim to estimate the top height and assess climate suitability across Europe under future climate conditions. One potential application of these models is in a decision support system (DSS) to inform tree species selection and management strategies in the context of climate change. Provided are the models, prediction outputs, and supporting information, as the underlying database is restricted by data use agreements.
Authors
Johannes Schumacher Alessandro Cescatti Gherardo Chirici Giovanni D’Amico Saverio Francini Johannes Hertzler Lauri Mehtätalo Gert-Jan Nabuurs Mats Nilsson Juho Pitkänen Johannes BreidenbachAbstract
The availability of reliable ground-truth data is one of the main bottlenecks for improving high-resolution forest attribute maps from Earth observation data. This is underpinned by the European Union (EU) Forest Strategy for 2030 that underscores the need for harmonized, cross-border forest resource assessments that integrate both remote sensing and field-based National Forest Inventory (NFI) data. However, confidentiality constraints on NFI plot coordinates present a significant barrier to aligning these datasets, thereby limiting the development of unified forest monitoring systems that can fully leverage the potential of Earth Observation data. To overcome these data-sharing limitations we explored the effectiveness of a privacy-enhancing technique, known as Federated Learning (FL), that is a form of distributed computing aimed at preserving the privacy and confidentiality of data owned by different organizations. This methodology has been tested for the collaborative modelling and mapping of forest timber volume across four European countries: Norway, Sweden, Finland, and Italy. We employed a time-series convolutional neural network (CNN) architecture tailored to integrate 40 years of Landsat or 7 years of Sentinel imagery and terrain variables with harmonized NFI data from more than 85,000 sample plots. This model architecture was used for the FL approach and compared to traditional country-specific and centralized modelling strategies. FL models achieved predictive performances comparable to the traditional models, which proofs the effectiveness of the proposed approach. Centralized or global models showed slightly reduced performance compared to the national models, highlighting the value of fine-tuning with local ground-truth data. By aligning with the EU’s forest monitoring objectives, FL facilitates the generation of harmonized models and maps of forest features, like timber volume and biomass, that are critical to support evidence-based forest policy and management. The findings underscore the potential of FL to transform collaborative environmental monitoring, particularly in domains where data confidentiality and interoperability are critical.
Abstract
Individual tree structure plays a key role in forest monitoring, biomass estimation, and ecological assessment. However, ground-based remote sensing methods such as terrestrial and mobile laser scanning frequently produce incomplete point clouds due to occlusion, particularly in the upper canopy. This limits the accuracy of derived structural metrics such as tree height or crown volume. In this study, we present a novel deep learning-based method to reconstruct the outer crown shape of coniferous trees from incomplete point clouds. Instead of completing the full tree structure, we focus on predicting the alpha-shape of the crown, enabling a more efficient and generalizable approach for structural reconstruction. We train a geometry-aware transformer model (AdaPoinTr) on synthetically generated partial tree crowns and evaluate its performance across three independent datasets encompassing different forest types and acquisition conditions. The model consistently improved the similarity metric Chamfer distance (CD) between partial and predicted tree crown shapes and reduced height estimation errors compared to using partial data alone (reduced bias from -11% to -3.5%). Our results demonstrate that this shape-based strategy enables the extraction of key tree-level parameters from incomplete data, offering a practical solution for gaining improved 3D forest structural information from cost-sensitive or logistically constrained forest monitoring acquisitions.
Abstract
Broadleaved tree species from Norwegian forests are a valuable raw material if this resource can be utilized effectively. Broadleaved tree species make for approximately one fourth of the total standing volume in Norway today. This paper provides detailed data on standing volume and annual volume increment of ash (Fraxinus excelsior), oak Quercus robur og Q. petrea), silver birch (Betula pendula), downy birch (Betula pubescens), aspen (Populus tremula), grey alder (Alnus incana), and black alder (Alnus glutinosa) in Norway, and give their distribution across the regions of Eastern Norway, Southern Norway, Western Norway, Trøndelag, and Northern Norway. Information on stand age, site quality, and diameter distribution will be provided.
Authors
Giovanni D’Amico Davide Botticelli Giacomo Marcelli Walter Mattioli Gherardo Chirici Elia Vangi Costanza Borghi Piermaria Corona Johannes Schumacher Johannes Breidenbach Yang Su Lauri Mehtätalo Saverio FranciniAbstract
This data article presents a multi-source dataset of satellite-based auxiliary data designed for forest modelling and monitoring. The dataset integrates annual medoid composites derived from Sentinel-1, Sentinel-2, and Landsat imagery, together with spectral indices, Landsat-based 3I3D change metrics, forest mask and forest type layers, and terrain variables derived from the Copernicus GLO-30 DEM, offering comprehensive information on forest cover, spectral behavior, and change metrics. It provides harmonized predictors across seven European countries, ensuring consistency, scalability, and ease of use for researchers developing or validating models to understand forest dynamics and estimate forest-related variables such as biomass or canopy recovery. A curated subset of the dataset is distributed via Zenodo, along with direct public access links to the complete multi-terabyte archive. The data support applications in forest biodiversity conservation, carbon monitoring, biomass modelling, and climate-change impact assessment.
Authors
Daniel Moreno-Fernández Patricia Adame Johannes Breidenbach Isabel Cañellas Christoph Fischer Kari T. Korhonen Jan Máslo Nerea Oliveira John Redmond Thomas Riedel Mitja Skudnik Iciar AlberdiAbstract
Forest diversity is a multidimensional concept comprising different components such as species diversity, functional diversity, structural diversity and genetic diversity. These diverse elements are recognised as being connected to the health and functioning of forest ecosystems and human well-being. However, information on forest diversity at broad spatial scales is scarce. Thus, the primary goal of this study is to quantify compositional diversity (i.e., tree species heterogeneity) and structural diversity (i.e., tree size heterogeneity) across a wide climatic gradient in European forest ecosystems, while also examining the influence of forest attributes and climatic variables on these two key components of forest diversity. Using harmonised data from eight European National Forest Inventories (n = 146,235 plots), we calculated Shannon’s Diversity Index as a measure of compositional and structural diversity. Finally, we estimated measures of forest diversity at three spatial scales ( α , β and γ -diversity) for each country. Basal area was positively related to compositional and structural diversity. In contrast, the quadratic mean diameter of the trees in each plot presented both positive and negative relationships with compositional and structural diversity, respectively. Climatic variables played a minor role, with precipitation and temperature showing a positive association with forest compositional and structural diversity. Furthermore, our findings revealed a positive link between compositional and structural diversity. Finally, the compound analyses of α , β , and γ-diversity emerged as key elements in interpreting compositional patterns at landscape scale. Results revealed strong scale dependence (from local to landscape level) in diversity metrics across countries, thereby highlighting the importance of reporting national forest information at multiple spatial scales.
Authors
Stefano Puliti Binbin Xiang Maciej Wielgosz Eivind Handegard Nicolas Cattaneo Marta Vergarechea Terje Gobakken Juha Hyyppä Erik Næsset Mikko Vastaranta Tuomas Yrttimaa Rasmus AstrupAbstract
Accurately determining the age of individual trees is important for understanding forest dynamics, tree growth, site productivity and describing ecological processes. Traditional methods, such as dendrochronological coring, are invasive, labor-intensive, and costly. This study investigates the use of deep learning (DL) to predict tree age from high-density laser scanning data as a scalable, non-invasive alternative. The dataset includes approximately 1700 tree point clouds from approx. 1 K trees across Norway, Sweden, and Finland, encompassing Norway spruce (Picea abies) and Scots pine (Pinus sylvestris) and a broad range of tree age and developmental stages, from young seedlings (1 year) to old trees (∼350 years). Data were collected using terrestrial, mobile, and high-density airborne laser scanning platforms, enabling the development of sensor-agnostic models. We evaluated multiple modelling approaches, from linear regression to transformer architectures, using both training-from-scratch and fine-tuning strategies. Models fine-tuned starting from pre-trained weights from ForestFormer3D's U-Net as well as the transformer architecture (PointTransformerV3) trained from scratch, proved effective for age regression (RMSE ≤23 years). Although our analysis was limited to two tree species, we demonstrated that a single joint age-estimation model can be successfully trained for both species. We demonstrate that models trained on high-resolution data can generalize to lower-resolution, less costly inputs, provided that data augmentations that mimic reduced resolutions are included during training. This study presents a data-driven framework for estimating tree age without destructive sampling. The findings support the potential for AI-based methods to complement or replace traditional age estimation techniques in forest inventory and monitoring.