Modelling Lake Glumsّ with learning

In this paper, we describe an application of Q 2 learning, a recently developed approach to machine learning in numerical domains, to the automated modelling of an aquatic ecosystem from measured data. We modelled the time behaviour of phytoplankton and zooplankton in Danish Lake Glumsّ using data collected by S.E. Jّrgensen. The novelty of Q 2 learning is in its paying attention to the qualitative correctness of induced numerical models. We assessed the results by, first, performing a comparison of numerical accuracy between our approach and some state-of-the-art numerical machine learning algorithms applied to the Glumsّ data, and second, we obtained expert evaluation of the induced models. The results show that Q 2 approach is at least comparable to competing methods in terms of numerical accuracy and gives good insight into domain phenomena.