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
Behaviour of Brown Bears Under Fluctuating Resource Availability
Tattoni , Clara , Corradini , Andrea , Chianucci , Francesco , Ciolli , Marco , Giusti , Roberta , Bragalanti , Natalia , Cagnacci , Francesca , Martinoli , Adriano , Preatoni , Damiano G. , Bisi , Francesco
alps beech mast damage home range maxent modelling ursus arctos
Mostra abstract
Mast seeding, the variable and intermittent production of seeds, has cascading effects on ecosystem functioning. This study explores its influence on the brown bear populations in the Italian Alps, focusing on beechnuts (Fagus sylvatica L.), the primary food source for bears in the region. Using historical data and field sampling, we estimated and mapped the annual seed biomass from 2007 to 2021 for the province of Trento. The energy content of beechnuts was assessed through high heating values, providing the caloric resources available. Data on beechnuts production, records of damages and GPS data from 16 Eurasian brown bears were integrated to perform a temporal and spatial analysis at home range and at landscape level. Standardised damages to beehives and livestock decreased during mast years, suggesting that bears met their trophic needs through natural food sources. In fact, bears used more agricultural areas and less beech forest during years of beech crop failure. At landscape level, agriculture and pasture areas close to beech forests and distant from cities showed a higher risk of damage, providing a tool to anticipate management actions. This work provides insights on the ecological dynamics and conservation implications of brown bears in the study area by mapping the spatial and temporal aspects of mast seeding and bear-related damages. © 2025 The Author(s). Ecology and Evolution published by British Ecological Society and John Wiley & Sons Ltd.
🔗 Vai alla pubblicazione
2025
Rivista
Ecology and Evolution
Dettagli
Vol. 15 (7)
DOI