Simultaneous prediction of multiple chemicalparameters of river water quality

Environmental studies form an increasingly popular application domain for machine learning and data mining techniques. In this paper we consider some applications of decision tree learning in the domain of river water quality. More speciically, we study a) the simultaneous prediction of multiple physico-chemical properties of the water from its biological properties using a single decision tree (as opposed to learning a diierent tree for each diierent property { we call this approach predict-ive clustering) and b) the prediction of past physico-chemical properties of the river water from its current biological properties. We discuss some experimental results that we believe are interesting both to the application domain experts and to the machine learning community.