Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species

The effect of different factors (spawning biomass, environmental conditions) on recruitment is a subject of great importance in the management of fisheries, recovery plans and scenario exploration. In this study, recently proposed supervised classification techniques, tested by the machine-learning community, are applied to forecast the recruitment of seven fish species of North East Atlantic (anchovy, sardine, mackerel, horse mackerel, hake, blue whiting and albacore), using spawning, environmental and climatic data. In addition, the use of the probabilistic flexible naive Bayes classifier (FNBC) is proposed as modelling approach in order to reduce uncertainty for fisheries management purposes. Those improvements aim is to improve probability estimations of each possible outcome (low, medium and high recruitment) based in kernel density estimation, which is crucial for informed management decision making with high uncertainty. Finally, a comparison between goodness-of-fit and generalization power is provided, in order to assess the reliability of the final forecasting models. It is found that in most cases the proposed methodology provides useful information for management whereas the case of horse mackerel is an example of the limitations of the approach. The proposed improvements allow for a better probabilistic estimation of the different scenarios, i.e. to reduce the uncertainty in the provided forecasts.

Quantitative pathways for Northeast Atlantic fisheries based on climate, ecological–economic and governance modelling scenarios

Here we present quantitative projections of potential futures for ecosystems in the North Atlantic basin generated from coupling a climate change-driven biophysical model (representing ecosystem and fish populations under climate change) and a scenario-driven ecological–economic model (representing fleets and industries under economic globalization). Four contrasting scenarios (Baseline, Fortress, Global Commons, Free Trade) were defined from the perspective of alternative regional management and governance of the oceanic basin, providing pathways for the future of ecosystems in the Northeast Atlantic basin by 2040. Results indicate that in the time frame considered: (1) the effects of governance and trade decisions are more significant in determining outcomes than the effects of climate change alone, (2) climate change is likely to result in a poleward latitudinal shift of species ranges and thus resources, with implications for exploitation patterns, (3) the level of fisheries regulation is the most important factor in determining the long term evolution of the fisheries system, (4) coupling climate change and governance impacts demonstrates the complex interaction between different components of this social–ecological system, (5) an important driver of change for the future of the North Atlantic and the European fishing fleets appears to be the interplay between wild fisheries and aquaculture development, and finally (6) scenarios demonstrate that the viability and profit of fisheries industries is highly volatile. This study highlights the need to explore basin-scale policy that combines medium to long-term environmental and socio-economic considerations, and the importance of defining alternative sustainable pathways.