To document

Abstract

1. 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. 2. 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). 3. 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. 4. 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.

To document

Abstract

Forest biodiversity is a multifaceted term encompassing tree and shrub diversity and the diversity of other life forms such as animals or fungi. Extensive forest monitoring networks such as National Forest Inventories or the International Co-operative Programme on Assessment and Monitoring of Air Pollution Effects on Forest plots have implemented biodiversity-monitoring protocols to satisfy increasing information demands. However, these protocols often evaluate biodiversity through potential biodiversity indicators (e.g., stand structure and deadwood), which may not provide sufficient information on other aspects of the current forest biodiversity status. In this study, we present the forest biodiversity monitoring results and lessons from a cross-country study to support large-scale monitoring systems. We developed, evaluated, and discussed harmonized protocols, mainly focused on birds and mammals, which extend beyond the traditional features captured in large-scale forest inventories. We leverage information from 30 intensively monitored plots established in six European countries to achieve these goals. The protocols were helpful in recording data that could be used to reproduce biodiversity-related attributes such as measures of forest structure, regeneration, deadwood features, and bird and mammal diversity. Specifically, field data on trees was used to describe structural features of forests such as stand composition and forest complexity. In contrast, composition and regeneration data provided helpful information for other biodiversity indicators. Data gathering to monitor bird and mammal diversity requires revisiting the plots, which involves greater economic investment and human effort. Once the bird and mammal data have been collected, advanced algorithms could facilitate and enhance the efficiency of the analyses. To optimize the monitoring efficiency, we recommend including these two new biodiversity assessments in a subset of extensive survey plots. Furthermore, using standard guidelines for these new assessments across all countries would facilitate the comparison and reporting of statistical data.

Forest illustration

Division of Forest and Forest Resources

A Decision Support System for emerging forest management alternatives


This project aims to develop advanced tree growth models using LiDAR-derived, high-density point cloud data to improve the simulation of forest dynamics under close-to-nature silvicultural practices. By modeling tree-level growth in structurally complex and heterogeneous stands, these models will support more accurate, spatially explicit forest simulations and inform sustainable and diversified forest management decisions.

Active Updated: 17.10.2025
End: jan 2027
Start: jan 2025
3D_gjengivelse av skog_Foto Stefano Puliti NIBIO

Division of Forest and Forest Resources

SFI SmartForest: Bringing Industry 4.0 to the Norwegian forest sector


SmartForest will position the Norwegian forest sector at the forefront of digitalization resulting in large efficiency gains in the forest sector, increased production, reduced environmental impacts, and significant climate benefits. SmartForest will result in a series of innovations and be the catalyst for an internationally competitive forest-tech sector in Norway. The fundamental components for achieving this are in place; a unified and committed forest sector, a leading R&D environment, and a series of progressive data and technology companies. 

Active Updated: 13.01.2026
End: sep 2028
Start: oct 2020