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
A deep learning approach for automatic mapping of poplar plantations using Sentinel-2 imagery
D'Amico , Giovanni , Francini , Saverio , Giannetti , Francesca , Vangi , Elia , Travaglini , Davide , Chianucci , Francesco , Mattioli , Walter , Grotti , Mirko , Puletti , Nicola , Corona , P. , Chirici , Gherardo
deep learning big data forest tree crops fully connected neural networks multitemporal classification tree species mapping
Mostra abstract
Poplars are one of the most widespread fast-growing tree species used for forest plantations. Owing to their distinct features (fast growth and short rotation) and the dependency on the timber price market, poplar plantations are characterized by large inter-annual fluctuations in their extent and distribution. Therefore, monitoring poplar plantations requires a frequent update of information–not feasible by National Forest Inventories due to their periodicity–achievable by remote sensing systems applications. In particular, the new Sentinel-2 mission, with a revisiting period of 5 days, represents a potentially efficient tool for meeting this need. In this paper, we present a deep learning approach for mapping poplar plantations using Sentinel-2 time series. A reference dataset of poplar plantations was available for a large study area of more than 46,000 km<sup>2</sup> in Northern Italy and served as training and testing data. Two classification methods were compared: (1) a fully connected neural network (also called multilayer perceptron), and (2) a traditional logistic regression. The performance of the two approaches was estimated through bootstrapping procedure with a confidence interval of 99%. Results indicated for deep learning an omission error rate of 2.77%±2.76%, showing improvements compared to logistic regression, omission error rate = 8.91%±4.79%. © 2021 Informa UK Limited, trading as Taylor & Francis Group.
🔗 Vai alla pubblicazione
2021
Rivista
GIScience and Remote Sensing
Dettagli
Vol. 58 (8) pp. 1352 - 1368
DOI