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.
2025
Authors
Linn Fenna Groeneveld Oksana Bekkevold Trond Bergskås Martin Linkogel Cord Luellmann Marit AlmvikAbstract
No abstract has been registered
Abstract
The precise spatially explicit data on land cover and land use changes is one of the essential variables for enhancing the quantification of greenhouse gas emissions and removals, which is relevant for meeting the goal of the European economy and society to become climate-neutral by 2050. The accuracy of the machine learning models trained on remote-sensed data suffers from a lack of reliable training datasets and they are often site-specific. Therefore, in this study, we proposed a method that integrates the bi-temporal analysis of the combination of spectral indices that detects the potential changes, which then serve as reference data for the Random Forest classifier. In addition, we examined the transferability of the pre-trained model over time, which is an important aspect from the operational point of view and may significantly reduce the time required for the preparation of reliable and accurate training data. Two types of vegetation losses were identified: woody coverage converted to non-woody vegetation, and vegetated areas converted to sealed surfaces or bare soil. The vegetation losses were detected annually over the period 2018–2021 with an overall accuracy (OA) above 0.97 and a Kappa coefficient of 0.95 for all time intervals in the study regions in Poland and Norway. Additionally, the pre-trained model’s temporal transferability revealed an improvement of the OA by 5 percentage points and the macroF1-Score value by 12 percentage points compared to the original model.
Abstract
No abstract has been registered
Authors
Junbin Zhao Simon Weldon Alexandra Barthelmes Erin Swails Kristell Hergoualc’h Ülo Mander Chunjing Qiu John Connolly Whendee L. Silver David I. CampbellAbstract
No abstract has been registered
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Gunhild Bødtker Claire Coutris Eva Marie-Louise Denison Åsa Frostegård Erik J. Joner Bjørn Tore Lunestad Elisabeth Henie Madslien Kaare Magne Nielsen Pål TrosvikAbstract
In this self-tasking scoping review, VKM will map research about the environmental impacts of biodegradable plastics, including biodegradation rates and material persistence in different environments and geographical regions, the influence on microbial ecology and activity, and ecotoxicological effects of materials and associated chemical substances. Related to this is also research associated with the development of methodology, standards, environmental risk assessment, life cycle impact analyses, material sources and properties of biodegradable plastics and products. The aim is to 1) determine the extent of evidence summarised in reviews and original research papers within this emerging research area and 2) map the evidence according to the materials and chemicals studied, types of environments and geographical regions covered, the hypotheses addressed, the type of endpoints assessed and the reported key findings. Systematic literature searches will be performed to identify the summarised evidence, applying APRIO to develop a tailored search protocol that addresses the multi- and cross-disciplinary nature of the research area. We will select and map the identified publications applying Rayyan and sort them into three categories based on their main scientific focus and aim of study: 1) material properties and application, 2) biodegradation and microbial ecology, and 3) ecotoxicology. There will be no geographical restrictions on the search and study selection, but in the data charting process we will highlight findings relevant to Norway and other Nordic countries. The current project adheres to the “Preferred Reporting Items for Systematic Reviews and MetaAnalyses extension for Scoping Reviews (PRISMA-ScR) Checklist” for protocol development and reporting. We will address uncertainties associated with research studies applying EFSA guidelines and their generic list of common types of uncertainty affecting scientific studies and assessments.
Authors
Heikki Korpunen Yrjö Nuutinen Paula Jylhä Lars Eliasson Aksel Granhus Juha Laitila Stephan Hoffmann Timo MuhonenAbstract
No abstract has been registered
Abstract
1. Field-based vegetation mapping is important for environmental assessments.Often, the area covered by a species is estimated visually within a reference frame.However, such assessments are prone to observer bias and a large variability. 2. We developed a deep learning pipeline relying on YOLOv8 models to segmentspecies and estimate the percentage cover (%) of Vaccinium myrtillus (blueberry)and Vaccinium vitis-idaea (lingonberry), two key understory species in borealforests. We used 138 nadir and downward-looking images of the forest floorcaptured in correspondence with 50 × 50 cm vegetation sub-plots assessedwithin National Forest Inventory (NFI) plots. First, we trained a bounding-boxframe detection model to crop the image to the same area assessed in the field.Second, we trained an instance segmentation model to classify species. Third,we flattened the class values into a semantic raster and estimated the species-specific cover by pixel counting. 3. We evaluated our method against an independent test set of 156 images andfound a root mean squared error (RMSE) of 8.82% for blueberry and 3.49% forlingonberry and no substantial systematic errors. An additional comparison withocular estimation by various field workers for the same plots showed that themodel estimates were within the range of estimates by field workers 8 out of 9times for blueberry and 7 out of 9 times for lingonberry. 4. The developed method shows promise in reducing observer bias and variabilityin vegetation surveys, thereby improving their consistency while significantlyreducing the time needed for species-specific coverage estimation. This isparticularly beneficial for repeated measurements and monitoring vegetationcover dynamics. However, as the method relies on RGB data, it is limited toestimating the percentage of visible species that are not obscured by others.Expanding the method to include a broader range of cover classes (e.g. grasses,rocks, logs) or species could automate the capture of crucial information