The objective of this thesis is the development of a method allowing the identification of factors leading to various radioactive contamination levels of the plants. The methodology suggested isbased on the use of a radioecological transfer model of the radionuclides through the environment (ASTRAL computer code) and a classification-tree method. Particularly, to avoid the instability problems of classification trees and to preserve the tree structure, a node level stabilizing technique is used. Empirical comparisons are carried out between classification trees built by this method (called REN method) and those obtained by the CART method. A similarity measure is defined to compare the structure of two classification trees. This measure is used to study the stabilizing performance of the REN method. The methodology suggested is applied to a simplified contamination scenario. By the results obtained, we can identify the main variables responsible of the various radioactive contamination levels of four leafy-vegetables (lettuce, cabbage, spinach and leek). Some extracted rules from these classification trees can be usable in a post-accidental context.