Placing biodiversity in ecosystem models without getting lost in translation

A key challenge to progressing our understanding of biodiversity’s role in the sustenance of ecosystem function is the extrapolation of the results of two decades of dedicated empirical research to regional, global and future landscapes. Ecosystem models provide a platform for this progression, potentially offering a holistic view of ecosystems where, guided by the mechanistic understanding of processes and their connection to the environment and biota, large-scale questions can be investigated. While the benefits of depicting biodiversity in such models are widely recognized, its application is limited by difficulties in the transfer of knowledge from small process oriented ecology into macro-scale modelling. Here, we build on previous work, breaking down key challenges of that knowledge transfer into a tangible framework, highlighting successful strategies that both modelling and ecology communities have developed to better interact with one another. We use a benthic and a pelagic case-study to illustrate how aspects of the links between biodiversity and ecosystem process have been depicted in marine ecosystem models (ERSEM and MIRO), from data, to conceptualisation and model development. We hope that this framework may help future interactions between biodiversity researchers and model developers by highlighting concrete solutions to common problems, and in this way contribute to the advance of the mechanistic understanding of the role of biodiversity in marine (and terrestrial) ecosystems.

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.