REPORT SVMSimulations2001/IDIAP Evaluation of SVM Binary Classification with Nonparametric Stochastic Simulations Kanevski, Mikhail EXTERNAL https://publications.idiap.ch/attachments/reports/2001/RR-01-07.pdf PUBLIC Idiap-RR-07-2001 2001 idiap The quality of Support Vector Machines binary classification of spatial environmental data is evaluated with geostatistical nonparametrtic conditional stochastic simulations. Equally probable realizations are generated and compared with SVM. Case study is based on the classification of porosity data. Results obtained confirm the efficiency of the SVM binary classification of spatial data