Nicolas Cattaneo


(+47) 412 20 885

Ås - Bygg H8

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.

Til dokument


Background Equatorward, rear-edge tree populations are natural monitors to estimate species vulnerability to climate change. According to biogeographical theory, exposition to drought events increases with increasing aridity towards the equator and the growth of southern tree populations will be more vulnerable to drought than in central populations. However, the ecological and biogeographical margins can mismatch due to the impact of ecological factors (topography, soils) or tree-species acclimation that can blur large-scale geographical imprints in trees responses to drought making northern populations more drought limited. Methods We tested these ideas in six tree species, three angiosperms (Fagus sylvatica, Quercus robur, Quercus petraea) and three gymnosperms (Abies alba, Pinus sylvestris and Pinus uncinata) by comparing rear-edge tree populations subjected to different degrees of aridity. We used dendrochronology to compare the radial-growth patterns of these species in northern, intermediate, and southern tree populations at the continental rear edge. Results and conclusions We found marked variations in growth variability between species with coherent patterns of stronger drought signals in the tree-ring series of the southern populations of F. sylvatica, P. sylvestris, and A. alba. This was also observed in species from cool-wet sites (P. uncinata and Q. robur), despite their limited responsiveness to drought. However, in the case of Q. petraea the intermediate population showed the strongest relationship to drought. For drought-sensitive species as F. sylvatica and P. sylvestris, southern populations presented more variable growth which was enhanced by cool-wet conditions from late spring to summer. We found a trend of enhanced vulnerability to drought in these two species. The response of tree growth to drought has a marked biogeographical component characterized by increased drought sensitivity in southern populations even within the species distribution rear edge. Nevertheless, the relationship between tree growth and drought varied between species suggesting that biogeographical and ecological limits do not always overlap as in the case of Q. petraea. In widespread species showing enhanced vulnerability to drought, as F. sylvatica and P. sylvestris, increased vulnerability to climate warming in their rear edges is forecasted. Therefore, we encourage the monitoring and conservation of such marginal tree populations.