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
Drivers of vascular species diversity on floodplain poplar stands: An integrated approach for ecological and functional assessment
Corli , Anna , Vannucchi , Francesca , Traversari , Silvia , Orsenigo , Simone , Giovannelli , Alessio , Chiarabaglio , Pier Mario , Chianucci , Francesco , Calfapietra , Carlo , Scartazza , Andrea , Mascherpa , Marco Carlo , Traversi , Maria Laura , Cristaldi , Luca , Trentanovi , Giovanni
soil properties stand structure management populus spp. soil enzymatic activities vascular plants diversity
Mostra abstract
Biodiversity restoration is pivotal to enhance natural ecological processes in riparian ecosystems, affected by intensive human impact. Improving the riparian area functionality through new plantations is an effective Nature-based Solution. Poplar plantations have great potential for preventing soil erosion and providing habitats, but their impact on biodiversity has been little studied. Aims of this study were to: (1) investigate the effect of different poplar woodland management on vascular species diversity; (2) define the main drivers of vascular plant species richness, community composition, invasiveness and functional strategies. In three sites (Po river, Italy), an integrated survey protocol was applied to assess vascular species diversity, stand structure and soil properties. For each site, three stands with different management (cultivated, semi-natural and natural) were surveyed. Differences among all stand structural parameters and the management types were found. Tree diameter did not change between natural and seminatural stands but mean quadratic diameter of seminatural stands (28.1 cm) was similar to cultivated ones (26.8 cm). While cultivated stands showed the highest species richness (mean 28 species), semi-natural stands showed the highest number of native species (82 %) and an efficient soil N cycle (microbial N limitation, MNL < 0). The total Ca and MNL in soil resulted the main drivers of species diversity in the studied poplar stands. Semi-natural stands highlighted the best trade-off amongst vascular plant species diversity, invasiveness and soil process. The used integrated approach was effective and extendable to ecological and functional assessment of poplar riparian forests under different management gradients. © 2025 The Authors
🔗 Vai alla pubblicazione
2025
Rivista
Forest Ecology and Management
Dettagli
Vol. 595
DOI