Publications
NIBIOs employees contribute to several hundred scientific articles and research reports every year. You can browse or search in our collection which contains references and links to these publications as well as other research and dissemination activities. The collection is continously updated with new and historical material.
2022
Abstract
No abstract has been registered
Authors
Svein Olav Krøgli Wendy Fjellstad Linda Aune-Lundberg Milena Chmielewska Agata Hościło Aneta LewandowskaAbstract
No abstract has been registered
Authors
Wendy Fjellstad Svein Olav Krøgli Linda Aune-Lundberg Milena Chmielewska Agata Hościło Kamila BelkaAbstract
No abstract has been registered
Authors
Wendy Fjellstad Svein Olav Krøgli Linda Aune-Lundberg Aneta Lewandowska Agata Hościło Milena ChmielewskaAbstract
No abstract has been registered
2021
Abstract
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.
Abstract
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.
Abstract
No abstract has been registered
Abstract
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.
Abstract
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.
Abstract
Aim Many thematic land cover maps, such as maps of vegetation types, are based on field inventories. Studies show inconsistencies among field workers in such maps, explained by inter-observer variation in classification and/or spatial delineation of polygons. In this study, we have tested a new method to assess the accuracy of these two components independently. Location Four study sites dominated by different ecosystems in southeast Norway. Methods We have used a vegetation-based land cover classification system adapted to a map scale of 1:5,000. First, a consensus map, a map that can be considered an approximation of a flawless map, was established. Secondly, the consensus map was adapted to test the accuracy of classification and polygon delineation independently. We used 10 field workers to generate a consensus map, and 14 new field workers (in pairs) to test the accuracy (n = 7). Results The results show that the accuracy of polygon delineation is lower than that of land cover classification. This is in contrast with previous studies, but previous research designs have not enabled a separation of the two accuracy components. Conclusion We recommend strengthening the training and harmonization of field workers in general, and increasing the emphasis on polygon delineation.