Publications
NIBIOs employees contribute to several hundred scientific articles and research reports every year. You can browse or search in our collection which contains references and links to these publications as well as other research and dissemination activities. The collection is continously updated with new and historical material.
2023
Abstract
Inthis study, we introduce Point2Tree, a modular and versatile framework that employs a three-tiered methodology, inclusive of semantic segmentation, instance segmentation, and hyperparameter optimization analysis, designed to process laser point clouds in forestry. The semantic segmentation stage is built upon the Pointnet++ architecture and is primarily tasked with categorizing each point in the point cloud into meaningful groups or ’segments’, specifically in this context, differentiating between diverse tree parts, i.e., vegetation, stems, and coarse woody debris. The category for the ground is also provided. Semantic segmentation achieved an F1-score of 0.92, showing a high level of accuracy in classifying forest elements. In the instance segmentation stage, we further refine this process by identifying each tree as a unique entity. This process, which uses a graph-based approach, yielded an F1-score of approximately 0.6, signifying reasonable performance in delineating individual trees. The third stage involves a hyperparameter optimization analysis, conducted through a Bayesian strategy, which led to performance improvement of the overall framework by around four percentage points. Point2Tree was tested on two datasets, one from a managed boreal coniferous forest in Våler, Norway, with 16 plots chosen to cover a range of forest conditions. The modular design of the framework allows it to handle diverse pointcloud densities and types of terrestrial laser scanning data.
Abstract
Sustainable forest management systems require operational measures to preserve the functional design of forest roads. Frequent road data collection and analysis are essential to support target-oriented and efficient maintenance planning and operations. This study demonstrates an automated solution for monitoring forest road surface deterioration using consumer-grade optical sensors. A YOLOv5 model with StrongSORT tracking was adapted and trained to detect and track potholes in the videos captured by vehicle-mounted cameras. For model training, datasets recorded in diverse geographical regions under different weather conditions were used. The model shows a detection and tracking performance of up to a precision and recall level of 0.79 and 0.58, respectively, with 0.70 mean average precision at an intersection over union (IoU) of at least 0.5. We applied the trained model to a forest road in southern Norway, recorded with a Global Navigation Satellite System (GNSS)−fitted dashcam. GNSS-delivered geographical coordinates at 10 Hz rate were used to geolocate the detected potholes. The geolocation performance over this exemple road stretch of 1 km exhibited a root mean square deviation of about 9.7 m compared to OpenStreetMap. Finally, an exemple road deterioration map was compiled, which can be used for scheduling road maintenance operations.
Authors
Risto Päivinen Rasmus Astrup Richard A. Birdsey Johannes Breidenbach Jonas Fridman Annika Kangas Pekka E. Kauppi Michael Köhl Kari T. Korhonen Vivian Kvist Johannsen François Morneau Thomas Riedel Klemens Schadauer Iddo K. WernickAbstract
No abstract has been registered
Abstract
Key message We studied size distributions of decay-affected Norway spruce trees using cut-to-length harvester data. The harvester data comprised tree-level decay and decay severity recordings from 101 final felling stands, which enabled to analyze relationships between size distributions of all and decay-affected trees. Distribution matching technique was used to transfer the size distribution of all trees into the diameter at breast height (DBH) distribution of decay-affected trees. Context Stem decay of Norway spruce (Picea abies [L.] Karst.) results in large economic losses in timber production in the northern hemisphere. Forest management planning typically requires information on tree size distributions. However, size distributions of decay-affected trees generally remain unknown impeding decision-making in forest management planning. Aims Our aim was to analyze and model relationships between size distributions of all and decay-affected Norway spruce trees at the level of forest stands. Methods Cut-to-length harvester data of 93,456 trees were collected from 101 final felling stands in Norway. For each Norway spruce tree (94% of trees), the presence and severity of stem decay (incipient and advanced) were recorded. The stand-level size distributions (diameter at breast height, DBH; height, H) of all and decay-affected trees were described using the Weibull distribution. We proposed distribution matching (DM) models that transform either the DBH or H distribution of all trees into DBH distributions of decay-affected trees. We compared the predictive performance of DMs with a null-model that refers to a global Weibull distribution estimated based on DBHs of all harvested decay-affected trees. Results The harvester data showed that an average-sized decay-affected tree is larger and taller compared with an average-sized tree in a forest stand, while trees with advanced decay were generally shorter and thinner compared with trees having incipient decay. DBH distributions of decay-affected trees can be matched with smaller error index (EI) values using DBH (EI = 0.14) than H distributions (EI = 0.31). DM clearly outperformed the null model that resulted in an EI of 0.32. Conclusions The harvester data analysis showed a relationship between size distributions of all and decay-affected trees that can be explained by the spread biology of decay fungi and modeled using the DM technique. Keywords Root and butt rot, Heterobasidion spp., Armillaria spp., Cut-to-length harvester, Forest management and planning
Abstract
No abstract has been registered
2022
Authors
Johannes Schumacher Håvard Toft Larsen Paul McLean Marius Hauglin Rasmus Astrup Johannes BreidenbachAbstract
The number of people affected by snow avalanches during recreational activities has increased over the recent years. An instrument to reduce these numbers are improved terrain classification systems. One such system is the Avalanche Terrain Exposure Scale (ATES). Forests can provide some protection from avalanches, and information on forest attributes can be incorporated into avalanche hazard models such as the automated ATES model (AutoATES). The objectives of this study were to (i) map forest stem density and canopy-cover based on National Forest Inventory and remote sensing data and, (ii) use these forest attributes as input to the AutoATES model. We predicted stem density and directly calculated canopy-cover in a 20 Mha study area in Norway. The forest attributes were mapped for 16 m × 16 m pixels, which were used as input for the AutoATES model. The uncertainties of the stem number and canopy-cover maps were 30% and 31%, respectively. The overall classification accuracy of 52 ski-touring routes in Western Norway with a total length of 282 km increased from 55% in the model without forest information to 67% when utilizing canopy cover. The F1 score for the three predicted ATES classes improved by 31%, 9%, and 6%.
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Saheba Bhatnagar Stefano Puliti Bruce Talbot Joachim Bernd Heppelmann Johannes Breidenbach Rasmus AstrupAbstract
Wheel ruts, i.e. soil deformations caused by harvesting machines, are considered a negative environmental impact of forest operations and should be avoided or ameliorated. However, the mapping of wheel ruts that would be required to monitor harvesting operations and to plan amelioration measures is a tedious and time-consuming task. Here, we examined whether a combination of drone imagery and algorithms from the field of artificial intelligence can automate the mapping of wheel ruts. We used a deep-learning image-segmentation method (ResNet50 + UNet architecture) that was trained on drone imagery acquired shortly after harvests in Norway, where more than 160 km of wheel ruts were manually digitized. The cross-validation of the model based on 20 harvested sites resulted in F1 scores of 0.69–0.84 with an average of 0.77, and in total, 79 per cent of wheel ruts were correctly detected. The highest accuracy was obtained for severe wheel ruts (average user’s accuracy (UA) = 76 per cent), and the lowest accuracy was obtained for light wheel ruts (average UA = 67 per cent). Considering the nowadays ubiquitous availability of drones, the approach presented in our study has the potential to greatly increase the ability to effectively map and monitor the environmental impact of final felling operations with respect to wheel ruts. The automated mapping of wheel ruts may serve as an important input to soil impact analyses and thereby support measures to restore soil damages.
Authors
Pekka E. Kauppi Gustav Stål Lina Arnesson-Ceder Isabella Hallberg Sramek Hans Fredrik Hoen Arvid Svensson Iddo K. Wernick Peter Högberg Tomas Lundmark Annika NordinAbstract
Planting new forests has received scientific and political attention as a measure to mitigate climate change. Large, new forests have been planted in places like China and Ethiopia and, over time, a billion hectares could become available globally for planting new forests. Sustainable management of forests, which are available to wood production, has received less attention despite these forests covering at least two billion hectares globally. Better management of existing forests would improve forest growth and help mitigate climate change by increasing the forest carbon (C) stock, by storing C in forest products, and by generating wood-based materials substituting fossil C based materials or other CO2-emission-intensive materials. Some published research assumes a trade-off between the timber harvested from existing forests and the stock of C in those forest ecosystems, asserting that both cannot increase simultaneously. We tested this assumption using the uniquely detailed forest inventory data available from Finland, Norway and Sweden, hereafter denoted northern Europe. We focused on the period 1960 – 2017, that saw little change in the total area covered by forests in northern Europe. At the start of the period, rotational forestry practices began to diffuse, eventually replacing selective felling management systems as the most common management practice. Looking at data over the period we find that despite significant increases in timber and pulp wood harvests, the growth of the forest C stock accelerated. Over the study period, the C stock of the forest ecosystems in northern Europe increased by nearly 70%, while annual timber harvests increased at the about 40% over the same period. This increase in the forest C stock was close to on par with the CO2-emissions from the region (other greenhouse gases not included). Our results suggest that the important effects of management on forest growth allows the forest C stock and timber harvests to increase simultaneously. The development in northern Europe raises the question of how better forest management can improve forest growth elsewhere around the globe while at the same time protecting biodiversity and preserving landscapes.