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.
2023
Authors
Stefano Puliti Grant Pearse Peter Surovy Luke Wallace Markus Hollaus Maciej Wielgosz Rasmus AstrupAbstract
The challenge of accurately segmenting individual trees from laser scanning data hinders the assessment of crucial tree parameters necessary for effective forest management, impacting many downstream applications. While dense laser scanning offers detailed 3D representations, automating the segmentation of trees and their structures from point clouds remains difficult. The lack of suitable benchmark datasets and reliance on small datasets have limited method development. The emergence of deep learning models exacerbates the need for standardized benchmarks. Addressing these gaps, the FOR-instance data represent a novel benchmarking dataset to enhance forest measurement using dense airborne laser scanning data, aiding researchers in advancing segmentation methods for forested 3D scenes. In this repository, users will find forest laser scanning point clouds from unamnned aerial vehicle (using Riegl sensors) that are manually segmented according to the individual trees (1130 trees) and semantic classes. The point clouds are subdivided into five data collections representing different forests in Norway, the Czech Republic, Austria, New Zealand, and Australia. These data are meant to be used either for developement of new methods (using the dev data) or for testing of exisitng methods (test data). The data splits are provided in the data_split_metadata.csv file. A full description of the FOR-instance data can be found at http://arxiv.org/abs/2309.01279
Authors
Stefano Puliti Grant Pearse Peter Surovy Luke Wallace Markus Hollaus Maciej Wielgosz Rasmus AstrupAbstract
The FOR-instance dataset (available at this https URL) addresses the challenge of accurate individual tree segmentation from laser scanning data, crucial for understanding forest ecosystems and sustainable management. Despite the growing need for detailed tree data, automating segmentation and tracking scientific progress remains difficult. Existing methodologies often overfit small datasets and lack comparability, limiting their applicability. Amid the progress triggered by the emergence of deep learning methodologies, standardized benchmarking assumes paramount importance in these research domains. This data paper introduces a benchmarking dataset for dense airborne laser scanning data, aimed at advancing instance and semantic segmentation techniques and promoting progress in 3D forest scene segmentation. The FOR-instance dataset comprises five curated and ML-ready UAV-based laser scanning data collections from diverse global locations, representing various forest types. The laser scanning data were manually annotated into individual trees (instances) and different semantic classes (e.g. stem, woody branches, live branches, terrain, low vegetation). The dataset is divided into development and test subsets, enabling method advancement and evaluation, with specific guidelines for utilization. It supports instance and semantic segmentation, offering adaptability to deep learning frameworks and diverse segmentation strategies, while the inclusion of diameter at breast height data expands its utility to the measurement of a classic tree variable. In conclusion, the FOR-instance dataset contributes to filling a gap in the 3D forest research, enhancing the development and benchmarking of segmentation algorithms for dense airborne laser scanning data.
Abstract
Inthis study, we introduce Point2Tree, a modular and versatile framework that employs a three-tiered methodology, inclusive of semantic segmentation, instance segmentation, and hyperparameter optimization analysis, designed to process laser point clouds in forestry. The semantic segmentation stage is built upon the Pointnet++ architecture and is primarily tasked with categorizing each point in the point cloud into meaningful groups or ’segments’, specifically in this context, differentiating between diverse tree parts, i.e., vegetation, stems, and coarse woody debris. The category for the ground is also provided. Semantic segmentation achieved an F1-score of 0.92, showing a high level of accuracy in classifying forest elements. In the instance segmentation stage, we further refine this process by identifying each tree as a unique entity. This process, which uses a graph-based approach, yielded an F1-score of approximately 0.6, signifying reasonable performance in delineating individual trees. The third stage involves a hyperparameter optimization analysis, conducted through a Bayesian strategy, which led to performance improvement of the overall framework by around four percentage points. Point2Tree was tested on two datasets, one from a managed boreal coniferous forest in Våler, Norway, with 16 plots chosen to cover a range of forest conditions. The modular design of the framework allows it to handle diverse pointcloud densities and types of terrestrial laser scanning data.
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Gry Alfredsen Lone Ross Michael Altgen Igor A. Yakovlev Anne-Cathrine Flyen Mari sand Austigaard Johan Mattsson Nanna Bjerregaard PedersenAbstract
No abstract has been registered
Authors
Gry Alfredsen Lone Ross Michael Altgen Igor A. Yakovlev Anne-Cathrine Flyen Mari sand Austigaard Johan Mattsson Nanna Bjerregaard PedersenAbstract
No abstract has been registered
Authors
Gry Alfredsen Lone Ross Michael Altgen Igor A. Yakovlev Anne-Cathrine Flyen Mari sand Austigaard Johan Mattsson Nanna Bjerregaard PedersenAbstract
No abstract has been registered
Authors
Jennifer James Chedly Kastally Katharina B. Budde Santiago C. González-Martínez Pascal Milesi Tanja Pyhäjärvi Martin Lascoux Paraskevi Alizoti Ricardo Alía Olivier Ambrosio Filippos A Aravanopoulos Georg Von Arx Albet Audrey Francisco Auñón Camilla Avanzi Evangelia Avramidou Francesca Bagnoli Marko Bajc Eduardo Ballesteros Evangelos Barbas José M García Del Barrio Cristina C Bastias Catherine Bastien Giorgia Beffa Raquel Benavides Vanina Benoit Frédéric Bernier Henri Bignalet Guillaume Bodineau Damien Bouic Sabine Brodbeck William Brunetto Jurata Buchovska Corinne Buret Melanie Buy Ana M Cabanillas-Saldaña Bárbara Carvalho Stephen Cavers Fernando Del Caño Sandra Cervantes Nicolas Cheval José M Climent Marianne Correard Eva Cremer Darius Danusevičius Benjamin Dauphin Jean-Luc Denou Bernard Dokhelar Alexis Ducousso Bruno Fady Patricia Faivre-Rampant Anna-Maria Farsakoglou Patrick Fonti Ioannis Ganopoulos Olivier Gilg Nicolas De Girardi René Graf Alan Gray Delphine Grivet Felix Gugerli Christoph Hartleitner Katrin Heer Enja Hollenbach Agathe Hurel Bernard Issenhuth Florence Jean Véronique Jorge Arnaud Jouineau Jan-Philipp Kappner Robert Kesälahti Florian Knutzen Sonja T Kujala Timo A Kumpula Katri Kärkkäinen Mariaceleste Labriola Celine Lalanne Johannes Lambertz Gregoire Le-Provost Vincent Lejeune Isabelle Lesur-Kupin Joseph Levillain Mirko Liesebach David López-Quiroga Ermioni Malliarou Jérémy Marchon Nicolas Mariotte Antonio Mas Silvia Matesanz Benjamin Meier Helge Meischner Célia Michotey Sandro Morganti Tor Myking Daniel Nievergelt Anne Eskild Nilsen Eduardo Notivol Dario Isidro Ojeda Alayon Sanna Olsson Lars Opgenoorth Geir Østreng Birte Pakull Annika Perry Sara Pinosio Andrea Piotti Christophe Plomion Nicolas Poinot Mehdi Pringarbe Luc Puzos Annie Raffin José A Ramírez-Valiente Christian Rellstab Dourthe Remi Oliver Reutimann Sebastian Richter Juan J Robledo-Arnuncio Odile Rogier Elisabet Martínez Sancho Outi Savolainen Simone Scalabrin Volker Schneck Silvio Schueler Ivan Scotti Sergio San Segundo Vladimir Semerikov Lenka Slámová Ilaria Spanu Jørn Henrik Sønstebø Jean Thevenet Mari Mette Tollefsrud Norbert Turion Fernando Valladares Giovanni G. Vendramin Marc Villar Marjana Westergren Johan WestinAbstract
New mutations provide the raw material for evolution and adaptation. The distribution of fitness effects (DFE) describes the spectrum of effects of new mutations that can occur along a genome, and is, therefore, of vital interest in evolutionary biology. Recent work has uncovered striking similarities in the DFE between closely related species, prompting us to ask whether there is variation in the DFE among populations of the same species, or among species with different degrees of divergence, that is whether there is variation in the DFE at different levels of evolution. Using exome capture data from six tree species sampled across Europe we characterized the DFE for multiple species, and for each species, multiple populations, and investigated the factors potentially influencing the DFE, such as demography, population divergence, and genetic background. We find statistical support for the presence of variation in the DFE at the species level, even among relatively closely related species. However, we find very little difference at the population level, suggesting that differences in the DFE are primarily driven by deep features of species biology, and those evolutionarily recent events, such as demographic changes and local adaptation, have little impact.
Authors
Clemens Blattert Mikko Mönkkönen Daniel Burgas Fulvio Di Fulvio Astor Toraño Caicoya Marta Vergarechea Julian Klein Markus Hartikainen Clara Antón Fernández Rasmus Astrup Michael Emmerich Nicklas Forsell Jani Lukkarinen Johanna Lundström Samuli Pitzén Werner Poschenrieder Eeva Primmer Tord Snäll Kyle EyvindsonAbstract
The European Union (EU) set clear climate change mitigation targets to reach climate neutrality, accounting for forests and their woody biomass resources. We investigated the consequences of increased harvest demands resulting from EU climate targets. We analysed the impacts on national policy objectives for forest ecosystem services and biodiversity through empirical forest simulation and multi-objective optimization methods. We show that key European timber-producing countries – Finland, Sweden, Germany (Bavaria) – cannot fulfil the increased harvest demands linked to the ambitious 1.5°C target. Potentials for harvest increase only exists in the studied region Norway. However, focusing on EU climate targets conflicts with several national policies and causes adverse effects on multiple ecosystem services and biodiversity. We argue that the role of forests and their timber resources in achieving climate targets and societal decarbonization should not be overstated. Our study provides insight for other European countries challenged by conflicting policies and supports policymakers.