Loading...
Pubblicazioni Scientifiche
Filtri di ricerca 3 risultati
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
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.
Assessment of UAV photogrammetric DTM-independent variables for modelling and mapping forest structural indices in mixed temperate forests
Giannetti
,
Francesca
,
Puletti
,
Nicola
,
Puliti
,
Stefano
,
Travaglini
,
Davide
,
Chirici
,
Gherardo
biodiversity
precision forestry
forest structure
forest inventory
airborne laser scanning
drone
dtm-independent
structure from motion
Mostra abstract
In the EU 2020 biodiversity strategy, maintaining and enhancing forest biodiversity is essential. Forest managers and technicians should include biodiversity monitoring as support for sustainible forest management and conservation issues, through the adoption of forest biodiversity indices. The present study investigates the potential of a new type of Structure from Motion (SfM) photogrammetry derived variables for modelling forest structure indicies, which do not require the availability of a digital terrain model (DTM) such as those obtainable from Airborne Laser Scanning (ALS) surveys. The DTM-independent variables were calculated using raw 3D UAV photogrammetric data for modeling eight forest structure indices which are commonly used for forest biodiversity monitoring, namely: basal area (G); quadratic mean diameter (DBH<inf>mean</inf>); the standard deviation of Diameter at Breast Height (DBH<inf>σ</inf>); DBH Gini coefficient (Gini); the standard deviation of tree heights (H<inf>σ</inf>); dominant tree height (H<inf>dom</inf>); Lorey's height (H<inf>l</inf>); and growing stock volume (V). The study included two mixed temperate forests areas with a different type of management, with one area, left unmanaged for the past 50 years while the other being actively managed. A total of 30 field sample plots were measured in the unmanaged forest, and 50 field plots were measured in the actively managed forest. The accuracy of UAV DTM-independent predictions was compared with a benchmark approach based on traditional explanatory variables calculated from ALS data. Finally, DTM-independent variables were used to produce wall-to-wall maps of the forest structure indices in the two test areas and to estimate the mean value and its uncertainty according to a model-assisted regression estimators. DTM-independent variables led to similar predictive accuracy in terms of root mean square error compared to ALS in both study areas for the eight structure indices (DTM-independent average RMSE<inf>%</inf> = 20.5 and ALS average RMSE<inf>%</inf> = 19.8). Moreover, we found that the model-assisted estimation, with both DTM-independet and ALS, obtained lower standar errors (SE) compared to the one obtained by model-based estimation using only field plots. Relative efficiency coefficient (RE) revealed that ALS-based estimates were, on average, more efficient (average RE ALS = 3.7) than DTM-independent, (average RE DTM-independent = 3.3). However, the RE for the DTM-independent models was consistently larger than the one from the ALS models for the DBH-related variables (i.e. G, DBH<inf>mean</inf>, and DBH<inf>σ</inf>) and for V. This highlights the potential of DTM-independent variables, which not only can be used virtually on any forests (i.e., no need of a DTM), but also can produce as precise estimates as those from ALS data for key forest structural variables and substantially improve the efficiency of forest inventories. © 2020 Elsevier Ltd
Estimating tree diversity in forest ecosystems by two-phase inventories
Corona
,
P.
,
Fattorini
,
Lorenzo
,
Franceschi
,
Sara
,
Marcheselli
,
Marzia
,
Pisani
,
Caterina
,
Chiavetta
,
U.
,
Puletti
,
Nicola
Mostra abstract
Several studies reveal that there is a strong interconnection between climate change and biodiversity. Indeed, estimating plant biodiversity is an important issue under forest ecosystem monitoring, which allows the evaluation of carbon storage and sequestration capacity. To this end, a two-phase strategy, suitably compatible with the most adopted sampling designs in large-scale forest inventories, is proposed. In the first phase, tessellation stratified sampling is performed by partitioning the study area into a grid of quadrats and by randomly selecting a point in each quadrat. The first-phase points are classified as forest or nonforest using remotely sensed imagery. In the second phase, a sample of points is selected from those classified as forest by means of simple random sampling without replacement. The second-phase points constitute the centers of circular plots that are visited in the field to record plant species (usually trees) and their abundance. Estimators of abundance and diversity and estimators of their variances are presented. The proposed strategy is applied in a forest area from Central Italy, as a case study. With respect to the sampling effort, the resulting estimates of relative standard errors are satisfactory, especially those regarding the overall total and diversity index estimators. The proposed statistical approach represents a suitable reference for integrated forest inventory frameworks effectively supporting biodiversity monitoring and assessment. © 2018 John Wiley & Sons, Ltd.