Pubblicazioni Scientifiche

Filtri di ricerca 2 risultati
Reset
Pubblicazioni per anno
Benchmarking tree species classification from proximally sensed laser scanning data: Introducing the FOR-species20K dataset
Puliti , Stefano , Lines , Emily R. , Müllerová , Jana , Frey , Julian , Schindler , Zoe , Straker , Adrian , Allen , Matthew J. , Winiwarter , Lukas , Rehush , Nataliia , Hristova , Hristina S. , Murray , Brent A. , Calders , Kim , Coops , Nicholas C. , Höfle , Bernhard , Irwin , Liam A.K. , Junttila , Samuli , Kruček , Martin , Krok , G. , Král , Kamil , Levick , Shaun R. , Lück , Linda , Missarov , Azim , Mokroš , M. , Owen , Harry Jon Foord , Stereńczak , Krzysztof Jan , Pitkänen , Timo P. , Puletti , Nicola , Saarinen , Ninni , Hopkinson , Chris Dennis , Terryn , Louise , Torresan , C. , Tomelleri , Enrico , Weiser , Hannah , Astrup , Rasmus
lidar remote sensing biodiversity deep learning point cloud classification single-tree inventory
Mostra abstract
Proximally sensed laser scanning presents new opportunities for automated forest ecosystem data capture. However, a gap remains in deriving ecologically pertinent information, such as tree species, without additional ground data. Artificial intelligence approaches, particularly deep learning (DL), have shown promise towards automation. Progress has been limited by the lack of large, diverse, and, most importantly, openly available labelled single-tree point cloud datasets. This has hindered both (1) the robustness of the DL models across varying data types (platforms and sensors) and (2) the ability to effectively track progress, thereby slowing the convergence towards best practice for species classification. To address the above limitations, we compiled the FOR-species20K benchmark dataset, consisting of individual tree point clouds captured using proximally sensed laser scanning data from terrestrial (TLS), mobile (MLS) and drone laser scanning (ULS). Compiled collaboratively, the dataset includes data collected in forests mainly across Europe, covering Mediterranean, temperate and boreal biogeographic regions. It includes scattered tree data from other continents, totaling over 20,000 trees of 33 species and covering a wide range of tree sizes and forms. Alongside the release of FOR-species20K, we benchmarked seven leading DL models for individual tree species classification, including both point cloud (PointNet++, MinkNet, MLP-Mixer, DGCNNs) and multi-view 2D-based methods (SimpleView, DetailView, YOLOv5). 2D Image-based models had, on average, higher overall accuracy (0.77) than 3D point cloud-based models (0.72). Notably, the performance was consistently >0.8 across scanning platforms and sensors, offering versatility in deployment. The top-scoring model, DetailView, demonstrated robustness to training data imbalances and effectively generalized across tree sizes. The FOR-species20K dataset represents an important asset for developing and benchmarking DL models for individual tree species classification using proximally sensed laser scanning data. As such, it serves as a crucial foundation for future efforts to classify accurately and map tree species at various scales using laser scanning technology, as it provides the complete code base, dataset, and an initial baseline representative of the current state-of-the-art of point cloud tree species classification methods. © 2025 The Author(s). Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society.
🔗 Vai alla pubblicazione
2025
Rivista
Methods in Ecology and Evolution
Dettagli
Vol. 16 (4) pp. 801 - 818
DOI
Sustainable forest planning: Assessing biodiversity effects of Triad zoning based on empirical data and virtual landscapes
Duflot , Rémi , Heinrichs , Steffi , Balducci , Lorenzo , Chianucci , Francesco , Hofmeister , Jeňýk , Paillet , Yoan , Trentanovi , Giovanni , Archaux , Frédéric , Boch , Steffen , Bouget , Christophe , Dvořák , Daniel , Fischer , Markus , Gosselin , Frédéric , Gosselin , Marion , Goßner , Martin M. , Holá , Eva , Hošek , Jan , Jung , Kirsten G. , Palice , Zdeněk , Renner , Swen C. , Weisser , Wolfgang W. , Nagel , Thomas A. , Burrascano , Sabina , Schall , Peter
forest management forestry biodiversity conservation gamma diversity landscape planning
Mostra abstract
The Triad framework seeks to balance the economic and ecological functions in forested landscapes by combining intensively, extensively, and unmanaged areas, assuming a higher support to biodiversity in extensively rather than in intensively managed forests. We quantified the effects of Triad zoning on biodiversity in (sub)montane eutrophic European beech forests. Using a European-wide multitaxon database and a “virtual” landscape approach (i.e., by resampling empirical data), we evaluated how the proportion of Triad management categories affected the landscape-level species diversity of birds, saproxylic beetles, vascular plants, epiphytic bryophytes, lichens, and wood-inhabiting fungi, as well as multitaxonomic diversity. The results varied greatly among taxonomic groups. Multitaxonomic diversity peaked in landscapes composed of 60% unmanaged and 40% intensively managed forests. While intensive management can benefit some taxa through the creation of open habitats, unmanaged forests are the backbone of biodiversity conservation, underlining the need to safeguard the remaining old-growth forests under natural dynamics, and to extend the current area of unmanaged forests in Europe. Extensive forest management, however, did not contribute to biodiversity conservation as expected. As withdrawing such a high proportion of European forest landscapes from management is unfeasible given the increasing demand for timber, efforts are needed to increase the presence of structural features supporting biodiversity into extensively managed forests. © © 2025 the Author(s).
🔗 Vai alla pubblicazione
2025
Rivista
Proceedings of the National Academy of Sciences of the United States of America
Dettagli
Vol. 122 (39)
DOI