Tree-related microhabitats (TreMs) play an important role in maintaining forest biodiversity and have recently received more attention in ecosystem conservation, forest management and research. However, TreMs have until now only been assessed by experts during field surveys, which are time-consuming and difficult to reproduce. In this study, we evaluate the potential of close-range terrestrial laser scanning (TLS) for semi-automated identification of different TreMs (bark, bark pockets, cavities, fungi, ivy and mosses) in dense TLS point clouds using machine learning algorithms, including deep learning. To classify the TreMs, we applied: (1) the Random Forest (RF) classifier, incorporating frequently used local geometric features and two additional self-developed orientation features, and (2) a deep Convolutional Neural Network (CNN) trained using rasterized multiview orthographic projections (MVOPs) containing top view, front view and side view of the point’s local 3D neighborhood. The results confirmed that using local geometric features is beneficial for identifying the six groups of TreMs in dense tree-stem point clouds, but the rasterized MVOPs are even more suitable. Whereas the overall accuracy of the RF was 70%, that of the deep CNN was substantially higher (83%). This study reveals that close-range TLS is promising for the semi-automated identification of TreMs for forest monitoring purposes, in particular when applying deep learning techniques.
For national and international reporting on forest available for wood supply (FAWS), harmonized data are needed. This information is required as forests provide goods for various sectors like the timber industry or the bioenergy sector. The effect of applying different thresholds to the three restriction classes (environmental, social and economic restriction) within the proposed reference definition for FAWS was evaluated. We applied the reference definition for FAWS to national data sets provided by five European National Forest Inventories using harmonized thresholds. The effects on FAWS area and growing stock were evaluated for each restriction and threshold. All countries within this study could report on protected areas. Social restrictions were not applied in any country, data on other restrictions are available but definitions vary. The application of common thresholds for restrictions proved difficult as effects vary between countries. The economic restriction is the most challenging to assess as many countries do not have corresponding data for direct calculation of, e.g., harvesting costs. Using proxies for harvesting costs was difficult, as common thresholds may not be applied in different countries. For standardized reporting, a FAWS definition should be developed that utilizes existing, harmonized indicators to describe restrictions.
3 April 2012 in European Journal of Forest Research