Logo des Repositoriums

Auflistung nach Autor:in "Džeroski, Sašo"

1 - 3 von 3
  • Konferenzbeitrag
    A Qualitative Multi-attribute Model for Economic and Ecological Evaluation of Genetically Modified Crops
    (Informatics for Environmental Protection - Networking Environmental Information, 2005) Bohanec, Marko; Messéan, Antoine; Scatasta, Sara; Džeroski, Sašo; Žnidaršič, Martin
    The use of genetically modified (GM) crops raises several concerns about their ecological and economic consequences. For the purpose of the European projects ECOGEN and SIGMEA, we develop qualitative multi-attribute hierarchical models for the assessment of GM and non-GM cropping systems. In this paper, we describe a model for the assessment of ecological and economic impacts of GM and non-GM maize cropping systems at the farm level for one year of cropping. In this model, cropping systems are described by the features: crop type, regional and farmlevel context, crop protection and crop management strategies, and expected characteristics of the yield. The assessment is based on four groups of ecological and two groups of economic indicators: biodiversity, soil biodiversity, water quality, greenhouse gasses, variable costs and the value of production. The paper presents the hierarchical structure and components of the model, and illustrates its application by assessing five typical cropping systems.
  • Konferenzbeitrag
    Modelling Outcrossing of Transgenes in Maize Between Neighboring Maize Fields
    (Informatics for Environmental Protection - Networking Environmental Information, 2005) Debeljak, Marko; Demšar, Damjan; Džeroski, Sašo; Schiemann, Joachim; Wilhelm, Ralf; Meier-Bethke, Sara
    We analyze data about the flow of pollen and more specifically the outcrossing from genetically modified maze to conventional maze to determine the most important factors influencing the flow. The machine learning technique of regression tree induction is used to build models that predict the degree of outcrossing from data on the relative position of the donor and recipient fields and the winds, as well as several variables derived from these (especially considering flowering times). The resulting models show that the distance between the fields plays a dominant role, followed by the angle and the percentage of appropriate wind (blowing from the donor to the recipient field).
  • Konferenzbeitrag
    Using Data Mining to Assess the Effects of Bt Baize on Soil Microarthropods
    (Informatics for Environmental Protection - Networking Environmental Information, 2005) Debeljak, Marko; Cortet, Jérôme; Demšar, Damjan; Džeroski, Sašo
    We investigate the effects of different factors (including climate and soil texture, crop type and farming practices), on the populations of soil microarthropods under agricultural field conditions. We use data mining to build predictive models that explicate these effects. The models built from data from three sites (two in France and one in Denmark) show a general positive effect of time since sowing and a specific negative effect of cultivating Bt maize at one of the three sites.