Benchmarking tree species classification from proximally sensed laser scanning data: Introducing the <scp>FOR</scp> ‐ <scp>species20K</scp> dataset

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 &gt;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.

Authors

Institutions

Publication Details

Journal
Methods in Ecology and Evolution
Published
2025-02-01
DOI
https://doi.org/10.1111/2041-210x.14503
Citations
21
Primary Topic
Remote Sensing and LiDAR Applications
Type
article
Field-Weighted Citation Impact
16.78

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Benchmarking tree species classification from proximally sensed laser scanning data: Introducing the FOR ‐ species20K dataset

Nataliia Rehush, Louise Terryn, Kim Calders, Azim Missarov et al.
21 citations
Methods in Ecology and Evolution
Remote Sensing and LiDAR Applications
16.78
article

Benchmarking tree species classification from proximally sensed laser scanning data: Introducing the FOR ‐ species20K dataset

Nataliia Rehush, Louise Terryn, Kim Calders, Azim Missarov, Zoe Schindler, Julian Frey, Krzysztof Stereńczak, Harry Owen, Chiara Torresan, Lukas Winiwarter, Adrian Straker, Rasmus Astrup, Jana Müllerová, Hannah Weiser, Grzegorz Krok, Nicholas C. Coops, Stefano Puliti, Samuli Junttila, Emily R. Lines, Martin Krůček, Hristina Hristova, Bernhard Höfle, Nicola Puletti, Kamil Král, Ninni Saarinen, Chris Hopkinson, Martin Mokroš, Liam Irwin, Brent A. Murray, Shaun R. Levick, Linda Lück, Matthew J. Allen, Timo Pitkänen, Enrico Tomelleri
article en
21 citations

Abstract

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 &gt;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.

Methods in Ecology and EvolutionVol. 16(4)
University of Lethbridge (CA), University of British Columbia (CA), TU Wien (AT), University of Freiburg (DE), Free University of Bozen-Bolzano (IT), University of Eastern Finland (FI), National Academies of Sciences, Engineering, and Medicine (US), Heidelberg University (DE), University of Cambridge (GB), Swiss Federal Institute for Forest, Snow and Landscape Research (CH), Charles Darwin University (AU), Natural Resources Institute Finland (FI), Jan Evangelista Purkyně University in Ústí nad Labem (CZ), Ghent University (BE), Norwegian Institute of Bioeconomy Research (NO), Landscape Research Institute (CZ), Instytut Badawczy Leśnictwa (PL), GFZ Helmholtz Centre for Geosciences (DE), National Research Council (IT), CSIRO Land and Water (AU), University College London (GB), University of Göttingen (DE)
UK Research and Innovation, European Commission, European Cooperation in Science and Technology, Deutsche Forschungsgemeinschaft, Academy of Finland, Austrian Science Fund, Norges Forskningsråd, Narodowe Centrum Badań i Rozwoju
Life in Land
Openalex Percentile: Top 0%
Remote Sensing and LiDAR Applications
16.78
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.