Misganu Debella-Gilo
Chief Engineer
Authors
Misganu Debella-GiloAbstract
Parts of the limited agricultural land area in Norway are taken up by buildings, roads, and other permanent changes every year. A method that detects such changes immediately after they have taken place is required in order to monitor the agricultural areas closely. To that end, Sentinel-2 satellite image time series (SITS) acquired during the summer of 2019 were used to detect the agricultural areas taken up by permanent changes such as buildings and roads. A deep-learning algorithm using 1D convolutional neural network (CNN), with the convolution in the temporal dimension, was applied to the SITS data. The training data was collected from the building footprints dataset filtered using a mono-temporal image aided with the areal resource map (AR5). The deep-learning model was trained and evaluated before being used for prediction in two regions of Norway. Procedures to reduce overfitting of the model to the training data were also implemented. The trained model showed a high level of accuracy and robustness when evaluated based on a test dataset kept out of the training process. The trained model was then used to predict new built-up areas in agricultural fields in two Sentinel-2 tiles. The prediction was able to detect areas taken by new buildings, roads, parking areas and other similar changes. The prediction was then evaluated with respect to the existing building footprints after a few post-processing procedures. A high percentage of the buildings were detected by the method, except for small buildings. The details of the methods and the results obtained, together with brief discussion, are presented in this paper.
Abstract
No abstract has been registered
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
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
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
Rapporten dokumenterer utvalgte eksempler på bruk av stordata (engelsk: big data) teknologi og metode i NIBIO. Det første eksemplet er knyttet til oppdatering av arealressurskartet AR5, hvor det undersøkes om stordata-tilnærming kan benyttes for å identifisere lokaliteter der kartet må oppdateres. De neste eksemplene er hentet fra fagområdet plantehelse og tar for seg mulighetene for å bruke stordata-metode for å bedre prediksjonsmodeller og gjenkjenning av for skadegjørere.
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Vibeke Stærkebye Nørstebø Svein Olav Krøgli Misganu Debella-Gilo Gerardo Alfredo Perez Valdes Kristin Tolstad Uggen Wenche DramstadAbstract
A transition to a bioeconomy implies an increased focus on efficient and sustainable use of biological resources. A common, but often neglected feature of these resources is their location dependence. To optimize their use, for example in bioeconomic industrial clusters, this spatial aspect should be integrated in analyses. Optimal design and localization of a bioeconomic cluster with respect to the various biological and non-biological resources required for the cluster, the composition of industrial facilities in the cluster, as well as the demands of the outputs of the cluster, is crucial for profitability and sustainability. We suggest that optimal design and location of bioeconomic clusters can benefit from the use of a Multicriteria Decision Analysis (MCDA) in combination with Geographic Information Systems (GIS) and Operations Research modeling. The integration of MCDA and GIS determines a set of candidate locations based on various criteria, including resource availability, accessibility, and usability. A quantitative analysis of the flow of resources between and within the different industries is then conducted based on economic Input-Output analysis. Then, the cluster locations with the highest potential profit, and their composition of industrial facilities, are identified in an optimization model. A case study on forest-based bioeconomic clusters in the Østfold county of Norway is presented to exemplify this methodology, the expectation being that further implementation of the method at the national level could help decision makers in the planning of a smoother transition from a fossil-based economy to a bioeconomy.
Abstract
No abstract has been registered
Abstract
Nation-wide Sentinel-2 mosaics were used with National Forest Inventory (NFI) plot data for modelling and subsequent mapping of spruce-, pine-, and deciduous-dominated forest in Norway at a 16 m × 16 m resolution. The accuracies of the best model ranged between 74% for spruce and 87% for deciduous forest. An overall accuracy of 90% was found on stand level using independent data from more than 42 000 stands. Errors mostly resulting from a forest mask reduced the model accuracies by ∼10%. The produced map was subsequently used to generate model-assisted (MA) and poststratified (PS) estimates of species-specific forest area. At the national level, efficiencies of the estimates increased by 20% to 50% for MA and up to 90% for PS. Greater minimum numbers of observations constrained the use of PS. For MA estimates of municipalities, efficiencies improved by up to a factor of 8 but were sometimes also less than 1. PS estimates were always equally as or more precise than direct and MA estimates but were applicable in fewer municipalities. The tree species prediction map is part of the Norwegian forest resource map and is used, among others, to improve maps of other variables of interest such as timber volume and biomass.
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Abstract
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.
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Misganu Debella-GiloAbstract
No abstract has been registered
Authors
Misganu Debella-Gilo Svein Olav Krøgli Vibeke Stærkebye Nørstebø Wenche Dramstad Gerardo Alfredo Perez ValdesAbstract
No abstract has been registered
Authors
Gerardo Alfredo Perez Valdes Vibeke Stærkebye Nørstebø Svein Olav Krøgli Wenche Dramstad Misganu Debella-Gilo Kristin Tolstad UggenAbstract
No abstract has been registered
Authors
Vibeke Stærkebye Nørstebø Gerardo Alfredo Perez Valdes Svein Olav Krøgli Wenche Dramstad Misganu Debella-Gilo Kristin Tolstad UggenAbstract
No abstract has been registered
Authors
Misganu Debella-GiloAbstract
No abstract has been registered
Authors
Misganu Debella-GiloAbstract
No abstract has been registered
Authors
Wenche Dramstad Vibeke Stærkebye Nørstebø Svein Olav Krøgli Misganu Debella-Gilo Gerardo A Pérez-ValdésAbstract
Aim: Identify where bioeconomic development would best be located to maximise both local resources and the reusable waste from potentially collaborating sectors. We seek to answer the questions like Where are the best locations for bioeconomic clusters and how should this be assessed? What are the tradeoffs, how can they be mapped and described, and are there any general major obstacles? What are the conditions that would aid in developing a smart bioeconomy and what are the spatial implications of different developments?
Authors
Jens Åström Wenche Dramstad Misganu Debella-Gilo Knut Anders Hovstad Sandra Charlotte Helene Åström Graciela RuschAbstract
In 2012, the Norwegian Environmental Agency funded an extension to the Global Pollination Project, coordinated by the FAO (Food and Agriculture Organization of the United Nations) to expand the number of connected countries from 7 fully participating to in total 13 countries. This international effort seeks to build capacity for pollination studies and add to the knowledge base for the Intergovernmental Platform for Biodiversity and Ecosystem Services (IPBES). IPBES is currently conducting its first fast track case study on pollination. Specifically, the Global Pollination Project implements the “Protocol to detect and assess pollination deficits in crops: a handbook for its use” (Vaissière et al. 2011), developed through the FAO. The proto-col outlines a unified method to investigate pollination and measure pollination deficits in vari-ous agricultural systems around the world. NINA (the Norwegian Institute for Nature Research) was tasked with setting up a Norwegian collaboration to implement the protocol in Norway, to analyse its applicability to Nordic conditions and evaluate its strength in relation to alternative research strategies. The present report is the result of this effort. This report does not communicate the final results of the analyses, as they will be conducted in the two larger “host-projects” that made the implementation of the protocol possible. Instead, it outlines the rationale of the protocol, and evaluates its potential for providing management rel-evant information on pollination deficits, with particular emphasis on Norway. We discuss the state and trends of pollination dependent crops in Norway, as a background for the need for pollination in Norwegian Agriculture. The protocol is general enough to be applied to a wide variety of settings, and we did not expe-rience any fundamental problems of implementing it in a Nordic setting. We did however notice challenges to an effective implementation, which might be especially pronounced in a Norwe-gian or Scandinavian setting. First, it can be difficult to find a wide enough range of factors that influence pollinators to efficiently analyse the importance of pollination without resorting to ma-nipulative treatments. For example, the amount of flower resources and fragmentation of habi-tat are factors known to influence pollinators. But many crops are spatially aggregated to rela-tively narrow valleys and therefore experience similar surroundings. Secondly, it can be chal-lenging to find enough replicate farms since Norway is a relatively small agricultural nation. Thirdly, pollinators in Norway (as in many other parts of the world) are intractably linked to ag-ricultural and animal husbandry practices that provide a diversity of flowering resources neces-sary for pollinating insects, yet these practices and resulting resources in the surrounding land-scape is not sufficiently captured by the survey protocol. The protocol is designed to estimate differences in yield given differences in pollination, and various methods are available to approach optimal pollination, that acts as benchmark. Esti-mating the effect of pollination on yield is the foundation to understanding the status of pollina-tion deficits for any crop. The protocol appears to be a successful effort to create a unified standard of measuring pollination and pollination deficits by this definition. It thus marks a great improvement for pollination research in agriculture internationally. Pollination, Ecosystem services, Bees, Bumble bees, Pollination deficit Protocol, FAO, IPBES, Policy, apple, red clover, Norway, pollinering, økosystemtjenester, bier, humler, protokoll for polline-ringsunderskudd, FAO, IPBES, eple, rødkløver
Abstract
No abstract has been registered
Abstract
The Norwegian landscape is changing as a result of forest regeneration within the cultural landscape, and forest expansion has impacts on accessibility, visibility, and landscape aesthetics, thereby affecting the country's tourism industry. This study aimed at identifying the potential areas of forest regeneration and anticipated subsequent landscape effects on different categories of tourist locations in southern Norway. Deforested areas with a potential for forest regeneration were identified from several map sources by GIS-analyses, and 180 tourist locations were randomly selected from the Norwegian national tourism database (Reiselivsbasen), and then buffered by 2 km radius for land cover classes. The findings revealed that approximately 15% of southern Norway has the climatic potential for future forest regeneration, in addition to 5% of cultivated land. Future forest regeneration will affect the landscapes surrounding the tourist locations of rural south Norway, and while the potential is nationwide, it is not uniformly distributed. Two important tourist landscape regions seem especially exposed to forest regeneration: the coastal heath region and the mountain landscapes. Large parts of these areas do not have sufficient numbers of domestic grazing animals necessary to maintain the present character of the landscape.