Simon Berg
Research Scientist
Biography
The majority of my work at NIBIO has revolved around managing and analysing large data sets. This work can be categorised into three main areas: analysing StandForD-files from forest machines, conducting extensive simulations of forest machines, and studying CANBUS data from timber trucks. In addition to this work, I have participated in more traditional forest operation research, such as time studies and work quality measurements.
Previus experiance
My academic journey began at the Swedish University of Agricultural Sciences (SLU), where I pursued a forester education (Master of Science in Forestry). My studies focused on raw material supply and production planning. I furthered my education at SLU with PhD studies in forest technology, considering "Technology and Systems for Stump Harvesting with Low Ground Disturbance". Following my PhD, I spent a year as a postdoctoral researcher at the University of Tokyo. There, I worked with small forwarders in steep terrain. I then returned to SLU to work on logistics around terminals and the transfer of GIS knowledge.
My PhD project, in more detail, included measuring ground disturbance, simulating the productivity of different stump harvesting systems, analysing costs, developing an experimental rig for stump twisting, and conducting time studies. This PhD project was part of the research school FIRST, which led me to spend a year on other research studies. These studies encompassed measuring temperature and gas emissions during the storage of peat and sawdust, conducting productivity studies, and investigating the variation in moisture content of forest fuel chips to estimate the necessary number of samples for different measurement precision. As a post-doc, my work included productivity studies and cost analysis of Japanese forwarders and separate loaders in steep terrain. I also collaborated on a study about the comminution of forest fuel. During my second tenure at SLU, I work with the potential benefits of open terminals and conducted an economic evaluation of different terminal locations, considering harvest, transportation, and capital costs.
Abstract
Time and motion studies in forest operations benefit from video-based analysis, but manual annotation is time consuming. This pilot study aims to reduce analysis time by developing a deep-learning framework that classifies dashcam video into four work elements: crane out, cutting and processing, driving, and processing. Using a 3D ResNet-50 (PyTorchVideo) trained on manually annotated clips, the model achieved validation F1 = 0.88 and precision = 0.90, showing that spatiotemporal CNNs can capture rele-vant motion and appearance cues in forest environments. Overfitting indicates that more diverse data and better class balance are needed, but the approach shows clear potential to scale automated work-element monitoring and efficiency analysis.
Abstract
Soil disturbance following forestry operations is influenced by multiple factors. Reducing disturbance requires placing strip and base roads in locations with minimal risk of disturbance. However, identifying these areas is a complex task. To address this, we have begun developing a forwarding risk index ranging from 1 to 100 that integrates several geographical information sources in the area around Oslo. This forwarding index seems to provide good estimates of areas with a higher risk of ground disturbance during forwarding operations at the sites used for development. With further development of geographical inputs, their combination into a risk index, and later on nationwide validation, the forwarding risk raster combined with a terrain map could improve the identification of suitable areas for forwarding trails. The risk raster was tested for path planning and performed well in areas with a low to moderate frequency of high-risk pixels but was less effective in areas with a high concentration of high-risk pixels. In these areas, an assessment of the potential ecological impact (erosion, sedimentation of streams, mobilisation of mercury, soil carbon impact, changes in hydrology, soil compaction) of ground disturbance is needed alongside the risk index to determine the least unsuitable trail locations.
Abstract
No abstract has been registered