Use of Self-Organizing Maps (SOM) for characterization of riverine phytoplankton associations in Hungary
Várbíró, Gábor; Ács, Éva.; Borics, Gábor; Érces, K.; Fehér, Giszella; Grigorszky, I.; Japport, T.; Kocsis, G.; Krasznai, E.; Nagy, K.; Nagy-László, Zs.; Pilinszky, Zs.; Kiss, Keve T.
The phytoplankton database of the Middle Danube Basin was analysed and evaluated in order to describe the characteristic algal assemblages of the rivers. The dataset were extracted from the database of the Hungarian monitoring network and academic institutions. We implemented the Kohonen Self Organizing Map (SOM) method by which we can visualize the assemblages in topology-preserving projection of two-dimensional space. The method is capable of evaluating large datasets (more than 1800 samples in the present investigation). As a result, we can identify the different algal communities which characterize different river types. The algal communities were described as different ratios of algal functional groups. Since some of the groups are in close relation with certain types of environmental pressure it is also possible to highlight those rivers or river sections (or those periods) which are far from the expected good ecological status.