Logo des Repositoriums

Auflistung nach Autor:in "Dzeroski, Saso"

1 - 4 von 4
  • Konferenzbeitrag
    Predicting Aggregate Properties of Soil Communities vs. Community Structure in an Agricultural Setting
    (Managing Environmental Knowledge, 2006) Demsar, Damjan; Dzeroski, Saso; Debeljak, Marko; Krogh, Paul Henning
    Increasing amounts of environmental data are being collected. With environmental data, we often encounter the situation of having to predict several target variables of similar type, such as biomasses of different species. This situation is usually handled by computing an aggregate target variable (like total biomass or a biodiversity measure) and then predicting the aggregate variable. Another possible (but rarely taken) approach is to model all target variables and then calculate the aggregate variable from the model outputs. In this paper, we try to answer the question whether the simpler approach of producing one model for the aggregate target variable is worse than the more complex approach of producing multiple models and then calculating the aggregate variable from the model outputs. We do this by taking a dataset describing the agricultural events and soil biological parameters as independent variables and a set of microarthropod species biomasses as dependent variables. We calculated several aggregate target variables such as total biomass, Shannon biodiversity and species richness from the original data. We build models to predict these directly, and also build separate predictive models for the biomass of the microarthropod species and calculate the aggregate target variables from the outputs of these models. We compared the aggregate variables calculated from the measured data, the aggregate variables predicted directly and the aggregate variables calculated from the outputs of the models for individual species using the Parson correlation coefficient and two additional error measures. Our results show, that in most cases first calculating the aggregate variables, and then learning models to predict these directly yields better results than modeling individual species and then calculating the aggregate variables from the predictions of these models.
  • Konferenzbeitrag
    Studying the Presence of Genetically Modified Variants in Organic Oilseed Rape by Using Relational Data Mining
    (Environmental Informatics and Systems Research, 2007) Ivanovska, Aneta; Vens, Celine; Dzeroski, Saso; Colbach, Nathalie
    The production of genetically-modified (GM) crops has increased rapidly over the last 10 years. The possibility of GM crops mixing with conventional or organic crops is becoming a problem and estimating the adventitious presence of GM seeds into conventional crop harvests presents a challenge. In this study we used outputs from a previously developed computer model for gene flow between GM and conventional oilseed rape to construct relational classification trees that predict the adventitious presence of GM seeds in the central field of a large-risk field pattern as a function of cultivation practices. Unlike propositional data mining methods, relational methods (relational classification trees) enable us to examine the relations among fields, for example, the influence of the neighbouring fields on the adventitious presence of GM seeds in a given field. For that purpose we used the relational data mining system TILDE.
  • Konferenzbeitrag
    Using Decision Trees to Predict Forest Stand Height and Canopy Cover from LANDSAT and LIDAR Data
    (Managing Environmental Knowledge, 2006) Dzeroski, Saso; Kobler, Andrej; Gjorgjioski, Valentin; Panov, Pance
    The motivation for this study was to improve the consistency and accuracy, and increase the spatial resolution of some of the supporting information to the forest monitoring system in Slovenia by using data mining techniques. Specifically we aim to generate raster maps with 25 m horizontal resolution of forest stand height and canopy cover, for the Kras region of Slovenia. We used predictive models based on multi-temporal Landsat data and calibrated it with high resolution airborne laser scanning (ALS) data. The visual inspection by a forestry expert of the resulting maps showed that the generated maps corresponded to the actual forest cover in the Kras region, both in terms of forest stand height as well as canopy cover.
  • Konferenzbeitrag
    Using Simulation Models and Data Mining to Study Co-Existence of GM/Non-GM Crops at Regional Level
    (Managing Environmental Knowledge, 2006) Ivanovska, Aneta; Panov, Pance; Colbach, Nathalie; Debeljak, Marko; Dzeroski, Saso; Messean, Antoine
    Genetically-modified (GM) crops increased their share in EU agriculture, so the adventitious presence of GM varieties in non-GM seeds and crops has become an issue and poses the problem of their co-existence with conventional and organic crops. Therefore, there is a need to propose appropriate measures at the farm and regional levels to minimize adventitious presence of GM crops. Outputs from the previously developed GENESYS model for gene flow between cropped and volunteer oilseed rape were used to make rule-based models that predict the rates of adventitious presence of GM seeds in the central field of a large-risk field pattern. Data aggregation was carried out to investigate if the regional variables improve the prediction quality of the rule-based model.