A Data-Oriented Predictive Ecology Approach to Modelling Fish Communities during Regime Shifts
Some spectacular collapses in fish stocks have occurred in the past 20 years but the most notable is the once largest cod stock in the world, the Northern cod stock off eastern Newfoundland, which experienced a 99% decline in biomass. Cod unfortunately, is not alone and there are stocks of various species that have been reduced to only a small percentage of stock sizes in recent history. Much of this effect is due to direct mortality on fish through fishing and subsequent indirect effects and weak linkages to other species. Some of these regions may have moved to an 'alternative stable state' or experienced a 'regime shift' and are unlikely to return to a cod dominated community for many years (possibly decades) without some chance environmental event beyond human control. We focus on using state-of-the-art computational techniques based upon Dynamic Bayesian Networks with latent variables to both integrate human expertise with extensive empirical data and model unmeasured factors to predict collapses in different fish communities. What is more we exploit functional equivalence between different communities to identify equivalent species in different regions and therefore predict functional collapse.
Trifonova, N. , Kenny, A. , Maxwell, D. , Duplisea, D. , et al. (2015) 'Spatio-temporal Bayesian network models with latent variables for revealing trophic dynamics and functional networks in fisheries ecology'. Ecological Informatics, 30 pp. 142 - 158. doi: 10.1016/j.ecoinf.2015.10.003
Trifonova, N. , Duplisea, D. , Kenny, A. and Tucker, A. (2014) 'A Spatio-Temporal Bayesian Network Approach for Revealing Functional Ecological Networks in Fisheries' , Symposium on Intelligent Data Analysis. Brussels. Springer Verlag
Trifonova, N. , Duplisea, D. , Kenny, A. , Maxwell, D. and Tucker, A. (2014) 'Incorporating Regime Metrics into Latent Variable Dynamic Models to Detect Early-Warning Signals of Functional Changes in Fisheries Ecology' , Discovery Science. Bled. Springer Verlag