Arnt Kristian Gjertsen

Research Scientist

(+47) 974 81 859

Ås R9

Visiting address
Raveien 9, 1430 Ås


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.


This paper describes the development and utility of the Norwegian forest resources map (SR16). SR16 is developed using photogrammetric point cloud data with ground plots from the Norwegian National Forest Inventory (NFI). First, an existing forest mask was updated with object-based image analysis methods. Evaluation against the NFI forest definitions showed Cohen's kappa of 0.80 and accuracy of 0.91 in the lowlands and a kappa of 0.73 and an accuracy of 0.96 in the mountains. Within the updated forest mask, a 16×16 m raster map was developed with Lorey's height, volume, biomass, and tree species as attributes (SR16-raster). All attributes were predicted with generalized linear models that explained about 70% of the observed variation and had relative RMSEs of about 50%. SR16-raster was segmented into stand-like polygons that are relatively homogenous in respect to tree species, volume, site index, and Lorey's height (SR16-vector). When SR16 was utilized in a combination with the NFI plots and a model-assisted estimator, the precision was on average 2–3 times higher than estimates based on field data only. In conclusion, SR16 is useful for improved estimates from the Norwegian NFI at various scales. The mapped products may be useful as additional information in Forest Management Inventories.

To document


The level of support to Norwegian agriculture is partly justified with reference to agriculture’s multifunctionality. The concept of multifunctionality involves the provision of so-called “public goods» by agriculture, in addition to the production of food and fibre. Examples of these public goods include cultural landscape, biodiversity, ecological functions, cultural heritage, the viability of rural areas, and food security. The overall aim of the research project “Operationalization of multifunctionality using the CAPRI modeling system» is to study the effects of policy instruments on agriculture’s multifunctionality by defining quantitative indicators for selected elements of agriculture’s multifunctionality that can be implemented in the agricultural sector model CAPRI. This working paper takes a first step towards the appropriate regionalization when multifunctionality is concerned. The current regionalization of the CAPRI model is at the county level. This approach fails when multifunctionality is concerned, because many issues of multifunctionaliy (e.g., cultural landscape aspects) are independent of administrative borders at that level. As the aim of the overall project is to study the effects of policy instruments on agriculture’s multifunctionality, it is important to design regions within the CAPRI model that to a greater extent exhibit similar characteristics with respect to aspects of agriculture’s multifunctionality. Accordingly, it is reasonable to assume that policy changes will have quite similar effects on the multifunctionality indicators within each of these CAPRI regions. This task has been addressed by performing a cluster analysis by which Norwegian municipalities have been grouped with respect to their performance on variables that are expected to describe different aspects of the multifunctionality of agriculture. This information will then later on be used to regionalize the CAPRI model accordingly. […]