Carolin Fischer

Head of Department/Head of Research

(+47) 967 41 326

Ås H8

Visiting address
Høgskoleveien 8, 1433 Ås


Information on tree height-growth dynamics is essential for optimizing forest management and wood procurement. Although methods to derive information on height-growth information from multi-temporal laser scanning data already exist, there is no method to derive such information from data acquired at a single point in time. Drone laser scanning data (unmanned aerial vehicles, UAV-LS) allows for the efficient collection of very dense point clouds, creating new opportunities to measure tree and branch architecture. In this study, we examine if it is possible to measure the vertical positions of branch whorls, which correspond to nodes, and thus can in turn be used to trace the height growth of individual trees. We propose a method to measure the vertical positions of whorls based on a single-acquisition of UAV-LS data coupled with deep-learning techniques. First, single-tree point clouds were converted into 2D image projections, and a YOLOv5 (you-only-look-once) convolutional neural network was trained to detect whorls based on a sample of manually annotated images. Second, the trained whorl detector was applied to a set of 39 trees that were destructively sampled after the UAV-LS data acquisition. The detected whorls were then used to estimate tree-, plot- and stand-level height-growth trajectories. The results indicated that 70 per cent (i.e. precision) of the measured whorls were correctly detected and that 63 per cent (i.e. recall) of the detected whorls were true whorls. These results translated into an overall root-mean-squared error and Bias of 8 and −5 cm for the estimated mean annual height increment. The method’s performance was consistent throughout the height of the trees and independent of tree size. As a use case, we demonstrate the possibility of developing a height-age curve, such as those that could be used for forecasting site productivity. Overall, this study provides proof of concept for new methods to analyse dense aerial point clouds based on image-based deep-learning techniques and demonstrates the potential for deriving useful analytics for forest management purposes at operationally-relevant spatial-scales.

To document


To mitigate climate change, several European countries have launched policies to promote the development of a renewable resource-based bioeconomy. These bioeconomy strategies plan to use renewable biological resources, which will increase timber and biomass demands and will potentially conflict with multiple other ecosystem services provided by forests. In addition, these forest ecosystem services (FES) are also influenced by other, different, policy strategies, causing a potential mismatch in proposed management solutions for achieving the different policy goals. We evaluated how Norwegian forests can meet the projected wood and biomass demands from the international market for achieving mitigation targets and at the same time meet nationally determined targets for other FES. Using data from the Norwegian national forest inventory (NFI) we simulated the development of Norwegian forests under different management regimes and defined different forest policy scenarios, according to the most relevant forest policies in Norway: national forest policy (NFS), biodiversity policy (BIOS), and bioeconomy policy (BIES). Finally, through multi-objective optimization, we identified the combination of management regimes matching best with each policy scenario. The results for all scenarios indicated that Norway will be able to satisfy wood demands of up to 17 million m3 in 2093. However, the policy objectives for FES under each scenario caused substantial differences in terms of the management regimes selected. We observed that BIES and NFS resulted in very similar forest management programs in Norway, with a dominance of extensive management regimes. In BIOS there was an increase of set aside areas and continuous cover forestry, which made it more compatible with biodiversity indicators. We also found multiple synergies and trade-offs between the FES, likely influenced by the definition of the policy targets at the national scale.