Pubblicazioni Scientifiche

Filtri di ricerca 4 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
A plot-level exploratory analysis of European forest based on the results from the BioSoil Forest Biodiversity project
Galluzzi , Marta , Giannetti , Francesca , Puletti , Nicola , Canullo , R. , Rocchini , Duccio , Bastrup-Birk , Annemarie M. , Chirici , Gherardo
data structure ground vegetation icp forests monitoring programme nfis
Mostra abstract
The lack of multi-dimensional data is one of the major gaps which limit the knowledge and the assessment possibilities of European forests. Nowadays, the most extensive and complete data on the European forest statuses are given by National Forest Inventories (NFIs) which provide information about the extent of forest’s resources and their composition and structure. Traditionally, NFIs collect data related to trees, with a limited consideration of other habitat components, such as ground vegetation. This information which goes beyond the mere arboreal component is instead essential for a more complete forest biodiversity assessment. This paper is aimed at introducing the ICP Forests LI-BioDiv database which resulted from BioSoil Forest Biodiversity, a large collaborative European project. This database is organized as a multi-dimensional forest geodatabase that contains forest structure and vegetation records collected in 19 European countries in the period of 2005–2008. The data were acquired from 3311 geocoded plots where several different types of data were gathered: stand-level general information, tree-level data, deadwood, canopy closure and floristic composition. This paper is structured in order to: (1) give a clear overview of the raw data available in the database and to (2) present an elaboration of raw data to calculate simple plot-level forest variables (biomass, deadwood volume, alpha diversity). On the basis of the results we achieved, the LI-BioDiv database appears useful mainly for research purposes aimed at studying cross-relationships between multiple forest variables and not for an operative use for monitoring and assessing European forest. In particular, we hope that this contribution can stimulate scientists to carry out cross-analysis of the database for defining future forest biodiversity indicators that could be introduced into the field protocols of the NFIs in Europe. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.
🔗 Vai alla pubblicazione
2019
Rivista
European Journal of Forest Research
Dettagli
Vol. 138 (5) pp. 831 - 845
DOI
TRY plant trait database – enhanced coverage and open access
Kattge , Jens , Bönisch , Gerhard , Díaz , Sandra M. , Lavorel , Sandra , Prentice , Iain Colin , Leadley , Paul W. , Tautenhahn , Susanne , Werner , Gijsbert , Aakala , Tuomas , Abedi , Mehdi , Acosta , Alicia Teresa Rosario , Adamidis , George C. , Adamson , Kairi , Aiba , Masahiro , Albert , Cécile Hélène , Alcántara , Julio M. , Alcázar C , Carolina , Aleixo , Izabela , Ali , Hamada E. , Amiaud , Bernard , Ammer , Christian , Amoroso , Mariano Martín , Anand , Madhur , Anderson , Carolyn G. , Anten , Niels P.R. , Antos , Joseph A. , Apgaua , Deborah Mattos Guimarães , Ashman , Tia Lynn , Asmara , Degi Harja , Asner , Gregory P. , Aspinwall , Michael J. , Atkin , Owen K. , Aubin , Isabelle , Baastrup-Spohr , Lars , Bahalkeh , Khadijeh , Bahn , Michael , Baker , Timothy R. , Baker , William J. , Bakker , Jan P. , Baldocchi , Dennis D. , Baltzer , Jennifer L. , Banerjee , Arindam , Baranger , Anne , Barlow , Jos B. , Barneche , Diego R. , Baruch , Zdravko , Bastianelli , Denis , Battles , John J. , Bauerle , William L. , Bauters , Marijn , Bazzato , Erika , Beckmann , Michael , Beeckman , Hans , Beierkuhnlein , Carl , Bekker , Renée M. , Belfry , Gavin , Belluau , Michaël , Beloiu Schwenke , Mirela , Benavides , Raquel , Benomar , Lahcen , Berdugo-Lattke , Mary Lee , Berenguer , Erika , Bergamin , Rodrigo Scarton , Bergmann , Joana , Carlucci , Marcos B. , Berner , Logan T. , Bernhardt-Römermann , Markus , Bigler , Christof , Bjorkman , Anne D. , Blackman , Chris J. , Blanco , Carolina Casagrande , Blonder , Benjamin Wong , Blumenthal , Dana M. , Bocanegra-González , Kelly Tatiana , Boeckx , Pascal , Bohlman , Stephanie Ann , Böhning-Gaese , Katrin , Boisvert-Marsh , Laura , Bond , William J. , Bond-Lamberty , Ben P. , Boom , Arnoud , Boonman , Coline C.F. , Bordin , Kauane Maiara , Boughton , Elizabeth H. , Boukili , Vanessa K.S. , Bowman , David M.J.S. , Bravo , Sandra Josefina , Brendel , Marco R. , Broadley , Martin R. , Brown , Kerry A. , Bruelheide , Helge , Brumnich , Federico , Bruun , Hans Henrik , Bruy , David , Buchanan , Serra Willow , Bucher , Solveig Franziska , Buchmann , Nina , Buitenwerf , Robert , Bunker , Daniel E. , Bürger , Jana
functional diversity data coverage data integration data representativeness plant traits try plant trait database
Mostra abstract
Plant traits—the morphological, anatomical, physiological, biochemical and phenological characteristics of plants—determine how plants respond to environmental factors, affect other trophic levels, and influence ecosystem properties and their benefits and detriments to people. Plant trait data thus represent the basis for a vast area of research spanning from evolutionary biology, community and functional ecology, to biodiversity conservation, ecosystem and landscape management, restoration, biogeography and earth system modelling. Since its foundation in 2007, the TRY database of plant traits has grown continuously. It now provides unprecedented data coverage under an open access data policy and is the main plant trait database used by the research community worldwide. Increasingly, the TRY database also supports new frontiers of trait-based plant research, including the identification of data gaps and the subsequent mobilization or measurement of new data. To support this development, in this article we evaluate the extent of the trait data compiled in TRY and analyse emerging patterns of data coverage and representativeness. Best species coverage is achieved for categorical traits—almost complete coverage for ‘plant growth form’. However, most traits relevant for ecology and vegetation modelling are characterized by continuous intraspecific variation and trait–environmental relationships. These traits have to be measured on individual plants in their respective environment. Despite unprecedented data coverage, we observe a humbling lack of completeness and representativeness of these continuous traits in many aspects. We, therefore, conclude that reducing data gaps and biases in the TRY database remains a key challenge and requires a coordinated approach to data mobilization and trait measurements. This can only be achieved in collaboration with other initiatives. © 2019 The Authors. Global Change Biology published by John Wiley & Sons Ltd
🔗 Vai alla pubblicazione
2020
Rivista
Global Change Biology
Dettagli
Vol. 26 (1) pp. 119 - 188
DOI
Comparing multisource harmonized forest types mapping: A case study from central italy
Vizzarri , Matteo , Chiavetta , U. , Chirici , Gherardo , Garfì , Vittorio , Bastrup-Birk , Annemarie M. , Marchetti , Marco
central italy forest area estimation forest categories forest nomenclature systems forest resources classification forest resources mapping forest types
Mostra abstract
The availability of common standardized geospatial information on composition, structure and distribution of forests is essential to support environmental actions, sustainable forest management and planning policies. Forest types maps are suitable tools for supporting both silvicultural and forest planning choices from local to global scale levels. For this reason local authorities may develop forest types maps independently, in which case a standardized/harmonized framework for their comparison and aggregation is essential. At the same time local forest types maps may not be directly related to pan-European forest resources assessments and classification systems. This paper presents results of the harmonization of four forest types maps available for central Italy. The process is based on a bottom-up approach aimed at maintaining the most detailed common nomenclature system across the different Regions. The final results, in terms of forest types area, are compared with several independent sources of information: (i) two forest maps, one developed at national level on the basis of the Corine Land Cover 2006, and one for high resolution forest/non forest classification developed at pan-European level; and (ii) two sample based inventories: the Italian National Forest Inventory (INFC) and the Italian Land Use Inventory (IUTI). The results show that the proposed bottomup harmonization approach is a suitable tool to guarantee the integrity and homogeneity of local forest types nomenclature systems, and to integrate such local data with European standards. ©iForest – Biogeosciences and Forestry
🔗 Vai alla pubblicazione
2014
Rivista
IForest
Dettagli
Vol. 8 pp. 59 - 66
DOI