Publikasjoner
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.
2022
Sammendrag
Det er ikke registrert sammendrag
2021
Sammendrag
I perioden 2003–2018 har det kun skjedd mindre endringer i det totale antallet sau og storfe som beiter i norsk utmark. Men når vi ser nærmere på hvor i landet dyrene er, finner vi at det har skjedd store endringer i den geografiske fordelingen av dyr på utmarksbeite. Dette kan blant annet ha mye å si for vegetasjon og dyreliv i utmarka.
Forfattere
Erik Framstad Knut Bjørkelo Vegar Bakkestuen Henrik Forsberg Mathiesen Megan Sara Nowell Geir-Harald Strand Zander VenterSammendrag
Det er ikke registrert sammendrag
Sammendrag
There are neither volume nor velocity thresholds that define big data. Any data ranging from just beyond the capacity of a single personal computer to tera- and petabytes of data can be considered big data. Although it is common to use High Performance Computers (HPCs) and cloud facilities to compute big data, migrating to such facilities is not always practical due to various reasons, especially for medium/small analysis. Personal computers at public institutions and business companies are often idle during parts of the day and the entire night. Exploiting such computational resources can partly alleviate the need for HPC and cloud services for analysis of big data where HPC and cloud facilities are not immediate options. This is particularly relevant also during testing and pilot application before implementation on HPC or cloud computing. In this paper, we show a real case of using a local network of personal computers using open-source software packages configured for distributed processing to process remotely sensed big data. Sentinel-2 image time series are used for the testing of the distributed system. The normalized difference vegetation index (NDVI) and the monthly median band values are the variables computed to test and evaluate the practicality and efficiency of the distributed cluster. Computational efficiencies of the cluster in relation to different cluster setup, different data sources and different data distribution are tested and evaluated. The results demonstrate that the proposed cluster of local computers is efficient and practical to process remotely sensed data where single personal computers cannot perform the computation. Careful configurations of the computers, the distributed framework and the data are important aspects to be considered in optimizing the efficiency of such a system. If correctly implemented, the solution leads to an efficient use of the computer facilities and allows the processing of big, remote, sensing data without the need to migrate it to larger facilities such as HPC and cloud computing systems, except when going to production and large applications.
Sammendrag
Rapid technological advances in airborne hyperspectral and lidar systems paved the way for using machine learning algorithms to map urban environments. Both hyperspectral and lidar systems can discriminate among many significant urban structures and materials properties, which are not recognizable by applying conventional RGB cameras. In most recent years, the fusion of hyperspectral and lidar sensors has overcome challenges related to the limits of active and passive remote sensing systems, providing promising results in urban land cover classification. This paper presents principles and key features for airborne hyperspectral imaging, lidar, and the fusion of those, as well as applications of these for urban land cover classification. In addition, machine learning and deep learning classification algorithms suitable for classifying individual urban classes such as buildings, vegetation, and roads have been reviewed, focusing on extracted features critical for classification of urban surfaces, transferability, dimensionality, and computational expense.
Sammendrag
Det er ikke registrert sammendrag
Sammendrag
Rapporten utforsker og diskuterer potensialet for økt bruk av Stordata (engelsk: big data) teknologi og metode innenfor instituttets arbeidsområder. I dag benyttes Stordata-tilnærminger til å løse forvaltningsstøtteoppgaver, samt til forskningsformål, særlig i sentrene for presisjonslandbruk og presisjonsjordbruk. Potensialet for økt bruk av Stordata innenfor instituttet er stort. For å realisere potensialet er det behov for god samordning mellom organisasjonsenhetene og utvikling av strategisk kompetanse på fagområdet.
Forfattere
Arnt Kristian GjertsenSammendrag
The national forest authority monitors forest regeneration on clear-cut areas annually and needs a more objective and unbiased sample. This can be solved with satellite images, and a method to detect new clear-cuts with time series of Sentinel-2 satellite images has been developed and tested. The 25 % percentile of the Normalized Burn Ratio (NBR) index, based on near-infrared and short wave infrared bands, is calculated and the differential (dNBR) between two years is used to detect new forest clearings. The method has been tested against a management plan with new clear-cuts in 2017. A total of 162 points, 81 in clear-cut and 81 in other stands, was used to test the accuracy. Based on the confusion matrix, the F1 score was 0.97 and the more balanced Matthews correlation coefficient 0.95.
Sammendrag
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.
Forfattere
Arnt Kristian GjertsenSammendrag
Det er ikke registrert sammendrag