Prediction of a complex system with few data: Evaluation of the effect of model structure and amount of data with dynamic bayesian network models. (August 2019)

• Record Type: Journal Article
• Authors: Maldonado, A.D.; Uusitalo, L.; Tucker, A.; Blenckner, T.; Aguilera, P.A.; Salmerón, A.
• Is Part Of: Environmental modelling & software. Volume 118(2019)
• Page Start: 281
• Page End: 297
• Publication Date: 2019-08
• Subjects: Baltic sea -- Ecosystem model -- Model comparison -- Regime shift -- Structural change -- Hidden variable; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2019.04.011
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: A major challenge in environmental modeling is to identify structural changes in the ecosystem across time, i.e., changes in the underlying process that generates the data. In this paper, we analyze the Baltic Sea food web in order to 1) examine potential unobserved processes that could affect the ecosystem and 2) make predictions on some variables of interest. To do so, dynamic Bayesian networks with different setups of hidden variables (HVs) were built and validated applying two techniques: rolling-origin and rolling-window. Moreover, two statistical inference approaches were compared at regime shift detection: fully Bayesian and Maximum Likelihood Estimation. Our results confirm that, from the predictive accuracy point of view, more data help to improve the predictions whereas the different setups of HVs did not make a critical difference in the predictions. Finally, the different HVs picked up patterns in the data, which revealed changes in different parts of the ecosystem. Highlights: Use dynamic Bayesian networks with hidden variables to analyze the Baltic Sea foodweb Analysis of unobserved processes revealed changes in different parts of the ecosystem Evaluation of accuracy of different model setups revealed no critical differences Comparison of 2 approaches to detect regime shift: Bayesian and Maximum Likelihood Analysis of amount of data needed to discover hidden variable pattern