Advances in Bayesian network modelling: Integration of modelling technologies. (January 2019)

• Record Type: Journal Article
• Authors: Marcot, Bruce G.; Penman, Trent D.
• Is Part Of: Environmental modelling & software. Volume 111(2019)
• Page Start: 386
• Page End: 393
• Publication Date: 2019-01
• Subjects: Bayesian networks -- Decision models -- Model integration -- Machine learning -- Model validation; 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.2018.09.016
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Bayesian network (BN) modeling is a rapidly advancing field. Here we explore new methods by which BN model development and application are being joined with other tools and model frameworks. Advances include improving areas of Bayesian classifiers and machine-learning algorithms for model structuring and parameterization, and development of time-dynamic models. Increasingly, BN models are being integrated with: management decision networks; structural equation modeling of causal networks; Bayesian neural networks; combined discrete and continuous variables; object-oriented and agent-based models; state-and-transition models; geographic information systems; quantum probability; and other fields. Integrated BNs (IBNs) are becoming useful tools in risk analysis, risk management, and decision science for resource planning and environmental management. In the near future, IBNs may become self-structuring, self-learning systems fed by real-time monitoring data. Such advances may make model validation difficult, and may question model credibility, particularly if based on uncertain sources of knowledge systems and big data. Highlights: Bayesian network (BN) modeling has become a popular tool in ecological science and environmental management. Innovations on network structure include improvements in Bayesian classifiers and machine-learning algorithms. We review the wide array of advances in BN modeling, particularly how they are being used and integrated in management decision networks. We offer cautions om validity and credibility of self-structuring and self-learning BN models developed from uncertain sources and big data.