Modelling The Growth Of AlgaeIn The Lagoon Of VeniceWith The Artificial Intelligence Tool GoldHorn
Boris Kompare, Sašo Džeroski, Viljem Križman · WIT transactions on ecology and the environment · 1997
Classical construction of ecological models follows one of the following two approaches: (1) either the measured data are analyzed with a statistical approach and a black-box statistical model is constructed, or (2) the model is deduced from basic (physical, chemical, etc.) principles and the measured data are used to calibrate and validate the model. A combination of the both ways is used very rarely, although it could combine the benefits of both. Machine learning tools (ML), developed within the area of artificial intelligence (AI), are able to analyze a data base (perform data mining), using also some domain (expert) knowledge. As a result, ML tools can automatically, or with limited expert help, induce compact and easy to understand models from measured data. In this paper a description of the ML tool GoldHorn that induces differential or difference (algebraic) equations from measured time series data is given. Its successful application to the prediction of algae growth in the Lagoon of Venice, Italy, is also described in detail. The model was induced using some background knowledge, as the tackled domain was too complex for data mining alone. Our experiments show that for noisy and complex domains inducing difference equations models could be more effective than inducing differential equations models. The induced (discovered) difference equation model for predicting algae growth in the Lagoon contains only one difference equation in contrast to classical models which contain several differential equations. Nevertheless, the simulation and predictive accuracy of the discovered model is comparable to the best deductionistic models of the Lagoon.