Global ETD Search

1	Vägledningar om skogsvårdslagens krav : Hur de efterlevs samt ombudens åsikter om dessa / Guidelines on the requirements of the Forest Conservation Act : How they are complied with and the attorneys´ views on them Kusén, Camilla, Wallin, Maria January 2020 (has links) The purpose of the study has been to investigate how well guidelines are observed in practice and also to see how the agents experience these and what they see for deficiencies and opportunities for improvement. This study is based on two studies. 34 items where guidance for rejuvenation harvesting took place were checked in the field. 104 representatives were asked to answer a questionnaire in which the questions focused on problems related to nature considerations and opportunities for improvement regarding the guidelines. The results show that the guidelines have been followed to a great extent and that the agents feel that they have benefited from the guidelines. The deficiencies in the guidelines were perceived to be too long and compact texts and that considerations described in the text were not highlighted in the map. Failure to observe the objects may, in the agents 'opinion, be partly due to the forest owners' opinions differing from the suggestions in the guidelines. The Swedish Forest Agency guidance Forestry Act nature conservation Dalarna Skogsstyrelsen vägledning skogsvårdslagen naturhänsyn Dalarna Forest Science Skogsvetenskap
2	Predicting forest strata from point clouds using geometric deep learning Arvidsson, Simon, Gullstrand, Marcus January 2021 (has links) Introduction: Number of strata (NoS) is an informative descriptor of forest structure and is therefore useful in forest management. Collection of NoS as well as other forest properties is performed by fieldworkers and could benefit from automation. Objectives: This study investigates automated prediction of NoS from airborne laser scanned point clouds over Swedish forest plots.Methods: A previously suggested approach of using vertical gap probability is compared through experimentation against the geometric neural network PointNet++ configured for ordinal prediction. For both approaches, the mean accuracy is measured for three datasets: coniferous forest, deciduous forest, and a combination of all forests. Results: PointNet++ displayed a better point performance for two out of three datasets, attaining a top mean accuracy of 46.2%. However only the coniferous subset displayed a statistically significant superiority for PointNet++. Conclusion: This study demonstrates the potential of geometric neural networks for data mining of forest properties. The results show that impediments in the data may need to be addressed for further improvements. Supervised learning Learning to rank Point-based models Shape inference PointNet layering layers classification ordingal regression forest agency ranking SLU 3D plots Computer Systems Datorsystem

Search results

Vägledningar om skogsvårdslagens krav : Hur de efterlevs samt ombudens åsikter om dessa / Guidelines on the requirements of the Forest Conservation Act : How they are complied with and the attorneys´ views on them

Predicting forest strata from point clouds using geometric deep learning