Abstract:Although wall-to-wall, accurate, and up-to-date forest composition maps at the stand level are a fundamental input for many applications, ranging from global environmental issues to local forest management planning, countrywide mapping approaches on the tree type level remain rare. This paper presents and validates an innovative remote sensing based approach for a countrywide mapping of broadleaved and coniferous trees in Switzerland with a spatial resolution of 3 m. The classification approach incorporates a random forest classifier, explanatory variables from multispectral aerial imagery and a Digital Terrain Model (DTM) from Airborne Laser Scanning (ALS) data, digitized training polygons and independent validation data from the National Forest Inventory (NFI). The methodological workflow was optimized for an area of 41,285 km 2 that is characterized by temperate forests within a complex topography. Whereas high model overall accuracies (0.99) and kappa (0.98) were achieved, the comparison of the tree type map with independent NFI data revealed significant deviations that are related to underestimations of broadleaved trees (median of −3.17%). Constraints of the tree type mapping approach are mostly related to the acquisition date and time of the imagery and the topographic (negative) effects on the prediction. A comparison with the most recent High Resolution Layers (HRL) forest 2012 from the European Environmental Agency revealed that the tree type map is superior regarding spatial resolution, level of detail and accuracy. The high-quality map achieved with the approach presented here is of great value for optimizing forest management and planning activities and is also an important information source for applications outside the forestry sector.

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.

No abstract

Forest structure reflects the forest disturbance regime, and can provide important information about 2 the rate of human impact. A better understanding of the structural variability and large-scale 3 dynamics of natural forests is crucial for "close-to-nature" forest management planning. In this 4 study, we developed a partly automated approach to assess the structure of potential primeval and 5 managed beech forests in the Ukrainian Carpathians using WorldView-2 imagery. We analyzed the 6 local (50 × 50 m scale) canopy closure of these forests by extracting the canopy gaps, and 7 determined four forest structure types ranging from very closed to low density. The occurrence and 8 frequencies of these structure types were significantly different in the primeval and managed beech 9 forests. The four forest structure types were predicted and mapped using multinomial logistic 10 regression based on the textural features derived from the original image bands and two vegetation 11 indices. A 10-fold cross-validation resulted in an overall accuracy of 83% and a kappa coefficient of 12 75%, with the highest agreement for the very closed structure type (87%) and the lowest for the 13 medium and low density (79%). The forest structure type maps can be helpful for planning 14 management activities in beech forests. 16Keywords: beech forests, structure types, canopy gap fraction, WorldView-2, Carpathian region. 33Disturbances are a driving force for forest stand development and affect forest structure. European for the costly additional work of surveying stand structures over large areas (Barrett et al. 2016). and canopy gap properties to characterize beech forests using VHR optical imagery exclusively. 66The objective of the present research was to design a partly automated approach to assess and map 67 the structure of potential primeval and managed beech forests in the Ukrainian Carpathians using 68WorldView-2 data. Assessing the differences in the structure of managed and primeval beech 69 forests can provide important information for managing beech forests sustainably, as well as for The study area is located in the southwest Ukraine ( 89Intensive use of the wood resources in the forests in the study area started approx. 70 years ago. 90According to Roth (1932), the forests in the upper part of the Borzhava river were defined as 91 primeval beech forests because of very limited human impact and high structural variability. These 92 forests were privately owned in the 1930s and were only occasionally used for hunting. Only the 93 narrow belts along the forests adjacent to alpine meadows (approx. 100 m wide) and to grassland in 94 the lower parts (100-300 m wide) were used to a limited extent for wood products (Roth 1932). 95Since the 1950s these forests have belonged to the state forest enterprise and have mostly been information about the acquisition parameters is given in Table 1. 105The original WorldView-2 image was converted to top-of-atmospheric (TOA) reflectance prior to 112The orthorectification revealed a r...

No abstract

Abstract. Depth estimation from a single image is a challenging task, especially inside the highly structured forest environment. In this paper, we propose a supervised deep learning model for monocular depth estimation based on forest imagery. We train our model on a new data set of forest RGB-D images that we collected using a terrestrial laser scanner. Alongside the input RGB image, our model uses a sparse depth channel as input to recover the dense depth information. The prediction accuracy of our model is significantly higher than that of state-of-the-art methods when applied in the context of forest depth estimation. Our model brings the RMSE down to 2.1 m, compared to 4 m and above for reference methods.

No abstract

No abstract