Use of qualitative constraints in modelling of the Lake Glumso. (8th November 2007)

• Record Type: Journal Article
• Authors: Vladusic, Daniel; Kompare, Boris; Bratko, Ivan
• Is Part Of: International journal of environment and pollution. Volume 31:Number 1/2(2007)
• Page Start: 107
• Page End: 124
• Publication Date: 2007-11-08
• Subjects: qualitative reasoning -- machine learning -- numerical prediction -- Lake Glumso -- modelling -- time behaviour -- phytoplankton -- zooplankton -- Denmark; Environmental policy -- Periodicals; Environmental engineering -- Periodicals; Environmental sciences -- Periodicals; Pollution -- Periodicals; 363.73
• Languages: English
• ISSNs: 0957-4352

Abstract

This paper describes modelling of time behaviour of phytoplankton and zooplankton in the Danish lake Glumso with a recently developed approach to machine learning in numerical domains, called Q2 learning. An essential part of this approach is qualitative constraints which were either handcrafted using knowledge from the Lotka-Volterra predator-prey model or induced directly from the collected data with a program called QUIN. The induced models were evaluated by a domain expert. We performed a comparison between numerical results of the Q2 learning approach and standard machine learning algorithms. The results suggest that use of qualitative constraints leads to more accurate quantitative predictions.