CLASSIFICATION OF ROMANIAN SALT WATER LAKES BY STATISTICAL METHODS

Investigation of the lake systems can provide a variety of information that can lead to the development of general concepts about how lakes function and respond to environmental changes. The purpose of this study is to assess the current classification of therapeutic lakes based on supervised learning methods applied to several biochemical characteristics of such lakes. In order to classify the therapeutic lakes in a separate class, a dataset consisting of 45 observations from 9 different basins and from three different altitude categories was analysed using clustering and classification methods.