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
No abstract has been registered
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Adrian Straker Stefano Puliti Johannes Breidenbach Christopher Kleinn Grant Pearse Rasmus Astrup Paul MagdonAbstract
Fine-grained information on the level of individual trees constitute key components for forest observation enabling forest management practices tackling the effects of climate change and the loss of biodiversity in forest ecosystems. Such information on individual tree crowns (ITC's) can be derived from the application of ITC segmentation approaches, which utilize remotely sensed data. However, many ITC segmentation approaches require prior knowledge about forest characteristics, which is difficult to obtain for parameterization. This can be avoided by the adoption of data-driven, automated workflows based on convolutional neural networks (CNN). To contribute to the advancements of efficient ITC segmentation approaches, we present a novel ITC segmentation approach based on the YOLOv5 CNN. We analyzed the performance of this approach on a comprehensive international unmanned aerial laser scanning (UAV-LS) dataset (ForInstance), which covers a wide range of forest types. The ForInstance dataset consists of 4192 individually annotated trees in high-density point clouds with point densities ranging from 498 to 9529 points m-2 collected across 80 sites. The original dataset was split into 70% for training and validation and 30% for model performance assessment (test data). For the best performing model, we observed a F1-score of 0.74 for ITC segmentation and a tree detection rate (DET %) of 64% in the test data. This model outperformed an ITC segmentation approach, which requires prior knowledge about forest characteristics, by 41% and 33% for F1-score and DET %, respectively. Furthermore, we tested the effects of reduced point densities (498, 50 and 10 points per m-2) on ITC segmentation performance. The YOLO model exhibited promising F1-scores of 0.69 and 0.62 even at point densities of 50 and 10 points m-2, respectively, which were between 27% and 34% better than the ITC approach that requires prior knowledge. Furthermore, the areas of ITC segments resulting from the application of the best performing YOLO model were close to the reference areas (RMSE = 3.19 m-2), suggesting that the YOLO-derived ITC segments can be used to derive information on ITC level.
Abstract
The aim of this study was to analyze the accuracy of predictions of dominant height, mean height, basal area, and volume from the nationwide forest attribute map (SR16). The analysis took advantage of field observations from 33 different forest inventory projects across Norway used for validation. Forest attributes for more than 5000 plots were predicted using non-stratified and stratified models of SR16 and the predictions were compared against corresponding ground reference values. Finally, the effect of different factors that might have influenced the prediction errors were analyzed using partial least squared regression (PLSR) to determine under which conditions the SR16 is less apt. The overall results across all plots were adequate (RMSE of 10%, MD of 2% for dominant and mean height; RMSE of 28%, MD of 4% for basal area; RMSE of 31%, MD of 5% for volume). However, when the accuracy was assessed locally for each inventory project, large differences in accuracy were observed. The MD% values for some inventory projects were substantial (>30% for basal area and volume). The results showed that stratification did not necessarily improve the results and that factors related to the forest structure had the greatest impact on the PLSR analysis.
Abstract
Monitoring and managing Earth’s forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in situ or aerial campaigns for forest assessments provide accurate data for analysis at regional level, scaling them to entire countries and beyond with high temporal resolution is hardly possible. In this work, we propose a method based on deep ensembles that densely estimates forest structure variables at country-scale with 10-m resolution, using freely available satellite imagery as input. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 syntheticaperture radar images into maps of five different forest structure variables: 95th height percentile, mean height, density, Gini coefficient, and fractional cover. We train and test our model on reference data from 41 airborne laser scanning missions across Norway and demonstrate that it is able to generalize to unseen test regions, achieving normalized mean absolute errors between 11% and 15%, depending on the variable. Our work is also the first to propose a variant of so-called Bayesian deep learning to densely predict multiple forest structure variables with well-calibrated uncertainty estimates from satellite imagery. The uncertainty information increases the trustworthiness of the model and its suitability for downstream tasks that require reliable confidence estimates as a basis for decision making. We present an extensive set of experiments to validate the accuracy of the predicted maps as well as the quality of the predicted uncertainties. To demonstrate scalability, we provide Norway-wide maps for the five forest structure variables.
Authors
Stefano PulitiAbstract
No abstract has been registered
Authors
Stefano PulitiAbstract
No abstract has been registered
Authors
Jaime Candelas Bielza Lennart Noordermeer Erik Næsset Terje Gobakken Johannes Breidenbach Hans Ole ØrkaAbstract
No abstract has been registered