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
Species dominance and above ground biomass in the Białowieża Forest, Poland, described by airborne hyperspectral and lidar data
Vaglio Laurin , Gaia , Puletti , Nicola , Grotti , Mirko , Stereńczak , Krzysztof Jan , Modzelewska , Aneta , Lisiewicz , Maciej , Sadkowski , Rafał , Kuberski , Łukasz , Chirici , Gherardo , Papale , Dario
climate change lidar aboveground biomass algorithm data set deciduous tree species diversity species richness vegetation dynamics bialowieza forest scolytinae
Mostra abstract
The objective of this research is to test and evaluate hyperspectral and lidar data to derive information on tree species dominance and above ground biomass in the Białowieża Forest in Poland. This forest is threatened by climate change, fire, bark beetles attacks, and logging, with changes in species composition and dominance. In this conservation valuable area, the monitoring of forest resources is thus critical. Results indicate that vegetation indices from hyperspectral data can support species dominance detection: using a Classification and Regression Trees algorithm the three main plot types (dominated by Deciduous, Spruce, and Pines species) were classified with an Overall Accuracy > 0.9. The accuracy decreased when a ‘Mixed’ group was added to account for very heterogeneous plots, and plots dominated by Spruce were not correctly detected. Hyperspectral vegetation indices were also used to estimate the level of species dominance in the forest plots, using a Multivariate Multiple Linear Regression model; the obtained accuracy varied according to groups, being higher for Deciduous (R<sup>2</sup> = 0.87), compared to Pines (R<sup>2</sup> = 0.61), and to Spruce-dominated plots (R<sup>2</sup> = 0.37). Lidar data were employed to estimate above ground biomass, using an exponential regression model; overall the R<sup>2</sup> resulted equal to 0.66 but ranged from 0.57 to 0.78 when considering subgroups according to species dominance; the addition of hyperspectral vegetation indices improved the result only for Pines. The illustrated methods provide a reliable description of important forest characteristics and simplify resource monitoring, supporting local authorities to address the challenges imposed by climate change and other forest threats. © 2020 The Authors
🔗 Vai alla pubblicazione
2020
Rivista
International Journal of Applied Earth Observation and Geoinformation
Dettagli
Vol. 92
DOI
Global airborne laser scanning data providers database (GlobALS)-A new tool for monitoring ecosystems and biodiversity
Stereńczak , Krzysztof Jan , Vaglio Laurin , Gaia , Chirici , Gherardo , Coomes , David Anthony , Dalponte , Michele , Latifi , Hooman , Puletti , Nicola
lidar forest database globals networking
Mostra abstract
Protection and recovery of natural resource and biodiversity requires accurate monitoring at multiple scales. Airborne Laser Scanning (ALS) provides high-resolution imagery that is valuable for monitoring structural changes to vegetation, providing a reliable reference for ecological analyses and comparison purposes, especially if used in conjunction with other remote-sensing and field products. However, the potential of ALS data has not been fully exploited, due to limits in data availability and validation. To bridge this gap, the global network for airborne laser scanner data (GlobALS) has been established as a worldwide network of ALS data providers that aims at linking those interested in research and applications related to natural resources and biodiversity monitoring. The network does not collect data itself but collects metadata and facilitates networking and collaborative research amongst the end-users and data providers. This letter describes this facility, with the aim of broadening participation in GlobALS. © 2020 by the authors.
🔗 Vai alla pubblicazione
2020
Rivista
Remote Sensing
Dettagli
Vol. 12 (11)
DOI
Trends of ungulate species in Europe: not all stories are equal
Cerri , Jacopo , Chirichella , Roberta , Arnold , Walter , Bartoš , Luděk , Borowik , Tomasz , Carranza , Juan , Chianucci , Francesco , Csányi , Sándor , Ericsson , Göran , Heurich , Marco , Kojola , Ilpo , Mysterud , Atle , Pokorny , Boštjan , Schmidt , Krzysztof , Šprem , Nikica , Vicente , Joaquín , Alagić , Ajša , Balčiauskas , Linas , Casaer , Jim , Cellina , Sandra , Done , Gundega , Find’o , Slavomír , Fonseca , Carlos M.M.S. , Gačić , Dragan P. , Melovski , Dime , Ozoliņš , Jânis , Papaioannou , Haritakis I. , Pusenius , Jyrki , Randveer , Tiit , Ruusila , Vesa , Saint-Andrieux , Christine , Veeroja , Rauno , Apollonio , Marco
hunting bags reforestation rural abandonment time-series analysis wild ungulates wildlife management
Mostra abstract
Wild ungulates have deep impacts on socio-ecological systems, and analyzing large-scale population trends in a multispecies set can identify their environmental and socio-economic drivers. We collected annual hunting bags (n = 11,046, period 1975–2018) of European roe deer, red deer, wild boar, fallow deer, mouflon, northern chamois and moose, across Europe. We identified different temporal trends in their hunting bags and evaluated the social and environmental drivers of their relative abundances. The number of harvested red deer and fallow deer, increased steadily across Europe, with minor differences among countries, despite variations in land use and climate. On the contrary, European roe deer harvests have decreased in six European countries since the late 1990s, probably due to landscape changes and locally also due to predation, interspecific competition, and/or increasing temperatures. Northern chamois harvests in Austria and Switzerland have decreased markedly, probably due to increasing temperatures, which decrease the survival of kids at high altitudes. Wild boar harvests have decreased in Poland, Estonia, Latvia, and Lithuania since the African Swine Fever outbreak in 2013–2014. Minor differences emerged between countries adopting different management regimes for wild ungulates. While many studies pointed out landscape changes as the cornerstone for the increase in wild ungulates across Europe, our research emphasizes important species-specific differences. There is a need to predict how landscape dynamics, climate change and recovering large carnivores will affect populations of species already showing signs of decline, like the European roe deer or the northern chamois. © The Author(s), under exclusive licence to Mammal Research Institute Polish Academy of Sciences 2026.
🔗 Vai alla pubblicazione
2026
Rivista
Mammal Research
Dettagli
Vol. 71 (2)
DOI