NIBIOs ansatte publiserer flere hundre vitenskapelige artikler og forskningsrapporter hvert år. Her finner du referanser og lenker til publikasjoner og andre forsknings- og formidlingsaktiviteter. Samlingen oppdateres løpende med både nytt og historisk materiale. For mer informasjon om NIBIOs publikasjoner, besøk NIBIOs bibliotek.



The size and location of agricultural fields that are in active use and the type of use during the growing season are among the vital information that is needed for the careful planning and forecasting of agricultural production at national and regional scales. In areas where such data are not readily available, an independent seasonal monitoring method is needed. Remote sensing is a widely used tool to map land use types, although there are some limitations that can partly be circumvented by using, among others, multiple observations, careful feature selection and appropriate analysis methods. Here, we used Sentinel-2 satellite image time series (SITS) over the land area of Norway to map three agricultural land use classes: cereal crops, fodder crops (grass) and unused areas. The Multilayer Perceptron (MLP) and two variants of the Convolutional Neural Network (CNN), are implemented on SITS data of four different temporal resolutions. These enabled us to compare twelve model-dataset combinations to identify the model-dataset combination that results in the most accurate predictions. The CNN is implemented in the spectral and temporal dimensions instead of the conventional spatial dimension. Rather than using existing deep learning architectures, an autotuning procedure is implemented so that the model hyperparameters are empirically optimized during the training. The results obtained on held-out test data show that up to 94% overall accuracy and 90% Cohen’s Kappa can be obtained when the 2D CNN is applied on the SITS data with a temporal resolution of 7 days. This is closely followed by the 1D CNN on the same dataset. However, the latter performs better than the former in predicting data outside the training set. It is further observed that cereal is predicted with the highest accuracy, followed by grass. Predicting the unused areas has been found to be difficult as there is no distinct surface condition that is common for all unused areas.


Denne publikasjonen presenterer en ny metodikk for estimering av endringer i lageret av jordkarbon som følge av arealbruksendringer på mineraljord. Metodikken er utviklet for bruk i den nasjonale rapporteringen av arealbrukssektoren under FNs klimakonvensjon. Metodikken baserer seg på den enkleste tilnærming i følge IPCC sine retningslinjer, en såkaldt Tier 1. Tier 1 metodikken baseres i stor grad på standardverdier fra retningslinjene (IPCC default), men trenger en kopling mot nasjonal arealinformasjon. Denne koplingen beskrives i rapporten. Metodikken tar utgangspunkt i standardverdier for lageret av jordkarbon (SOCREF). Disse er basert på jordtype-grupperinger og klimasone som stammer fra en verdensdekkende jorddatabase. Endringer i jordkarbon etter arealbruksendring estimeres ved hjelp av SOCREF i kombinasjon med et sett faktorer (også standardverdier) som er arealbruksavhengige. Metodikken legger til grunn at endringer i jordkarbon skjer lineært over 20 år (ifølge 2006 IPCC Guidelines). Grunnleggende informasjon for å kunne kople standardverdier mot arealer på en konsistent måte er stort sett manglende for Norge på nasjonal skala. Rapporten gir derfor detaljert informasjon om de datakildene som har vært brukt til å kunne definere hvilke standariserte verdier som tilhører et bestemt areal i overgang....



Planning sustainable use of land resources and environmental monitoring benefit from accurate and detailed forest information. The basis of accurate forest information is data on the spatial extent of forests. In Norway land resource maps have been carefully created by field visits and aerial image interpretation for over four decades with periodic updating. However, due to prioritization of agricultural and built-up areas, and high requirements with respect to the map accuracy, forest areas and outfields have not been frequently updated. Consequently, in some part of the country, the map has not been updated since its first creation in the 1960s. The Sentinel-2 satellite acquires images with high spatial and temporal resolution which provides opportunities for creating cloud-free mosaic images over areas that are often covered with clouds. Here, we combine object-based image analysis with machine learning methods in an automated framework to map forest area in Sentinel-2 mosaic images. The images are segmented using the eCogntionTM software. Training data are collected automatically from the existing land resource map and filtered using height and greenness information so that the training samples certainly represent their respective classes. Two machine learning algorithms, namely Random Forest (RF) and the Multilayer Perceptron Neural Network (MLP), are then trained and validated before mapping forest area. The effects of including and excluding some features on the classification accuracy is investigated. The results show that the method produces forest cover map at very high accuracy (up to 97%). The MLP performs better than the RF algorithm both in classification accuracy and in robustness against inclusion and exclusion of features.