Exploring capelin (Mallotus villosus) population dynamics using Empirical Dynamic Modelling (EDM)

Abstract

Capelin (Mallotus villosus) populations on the Newfoundland shelf collapsed in the early 1990s, coinciding with a regime shift and greatly reduced capelin and groundfish biomasses which both persist to this day. The biphasic nature of this stock’s history suggest it may experience nonlinear dynamics, which are difficult to predict using linear models. This study explores the application of Empirical Dynamic Modelling (EDM) nonlinear, nonparametric time series forecasting tools to capelin biomass data, seeking to detect nonlinear dynamics, compare performance of linear and nonlinear multivariate predictive models, identify drivers of capelin biomass using convergent cross-mapping, and measure the sign and strength of capelin species interactions. We found capelin dynamics were nonlinear, and multivariate EDM predictive models returned equal or improved model diagnostics to linear models in most situations. We identified long-term climate dynamics and timing of sea ice retreat as the primary drivers of capelin dynamics, but some indications of potential top-down effects from Greenland halibut were also detected. Atlantic cod biomass, and capelin catch were investigated as potential drivers of capelin dynamics, but both were found more likely to be driven by capelin dynamics. Overall, our results support the idea that capelin dynamics are mostly bottom-up driven, and that capelin itself is a driver of its predators, suggesting that the overall ecosystem may be largely bottom-up driven. This study also clearly identifies the utilities of EDM as a complementary tool for stock assessments by detecting and forecasting nonlinear stock dynamics, and identifying and characterizing relationships between stock biomass and the factors which drive it.