Linda Aune-Lundberg
Research Scientist
(+47) 995 78 533
linda.aune-lundberg@nibio.no
Place
Tromsø
Visiting address
Holtvegen 66, 9016 Tromsø
Abstract
The study focuses on ecosystem services, historical aspects, and natural diversity. Specifically, it assesses possible proxies for investigating a set of cultural ecosystem services from the Norwegian agricultural landscape. Agricultural areas on the Norwegian land cover map surrounded by a 100 m wide buffer zone were analyzed for recorded historical buildings, cultural heritage sites, red-listed vascular plant species (defined as being at varying degrees at risk of extinction), and red-listed nature types (defined as endangered or vulnerable). The results indicate significant contributions from agricultural landscapes with respect to historical buildings, cultural heritage sites, and red-listed plant species. Regarding red-listed nature types, the contributions were diverse. The ecosystem proxies investigated showed increasing distribution trends with increasing proportions of agricultural landscapes in the spatial units, with a sharp increase with smaller area sizes. However, for cultural heritage sites the trend was different when the proportion of the agricultural landscape was below 25%; it showed a very slow increase. In conclusion, the study highlights the agricultural landscape’s diverse contributions to the investigated ecosystem services in Norway, prompting the need for further research on additional ecosystem services to ensure the continued delivery of environmental and social well-being.
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