Search

For decades, fish recruitment has been a subject of intensive research with stock–recruitment models commonly used for recruitment prediction often only explaining a small fraction of the inter-annual recruitment variation. The use of environmental information to improve our ability to predict recruitment, could contribute considerably to fisheries management. However, the problem remains difficult because the mechanisms behind such complex relationships are often poorly understood; this in turn, makes it difficult to determine the forecast estimation robustness, leading to the failure of some relationships when new data become available. The utility of machine learning algorithms such as artificial neural networks (ANNs) for solving complex problems has been demonstrated in aquatic studies and has led many researchers to advocate ANNs as an attractive, non-linear alternative to traditional statistical methods. The goal of this study is to design a Baltic cod recruitment model (FishANN) that can account for complex ecosystem interactions. To this end, we (1) build a quantitative model representation of the conceptual understanding of the complex ecosystem interactions driving Baltic cod recruitment dynamics, and (2) apply the model to strengthen the current capability to project future changes in Baltic cod recruitment. FishANN is demonstrated to bring multiple stressors together into one model framework and estimate the relative importance of these stressors while interpreting the complex nonlinear interactions between them. Additional requirements to further improve the current study in the future are also proposed.

In the face of increasing anthropogenic pressures acting on the Earth system, urgent actions are needed to guarantee efficient resource management and sustainable development for our growing human population. Our oceans - the largest underexplored component of the Earth system - are potentially home for a large number of new resources, which can directly impact upon food security and the wellbeing of humanity. However, the extraction of these resources has repercussions for biodiversity and the oceans ability to sequester green house gases and thereby climate. In the search for new resources to unlock the economic potential of the global oceans, recent observations have identified a large unexploited biomass of mesopelagic fish living in the deep ocean. This biomass has recently been estimated to be 10 billion metric tonnes, 10 times larger than previous estimates however the real biomass is still in question. If we are able to exploit this community at sustainable levels without impacting upon biodiversity and compromising the oceans’ ability to sequester carbon, we can produce more food and potentially many new nutraceutical products. However, to meet the needs of present generations without compromising the needs of future generations, we need to guarantee a sustainable exploitation of these resources. To do so requires a holistic assessment of the community and an understanding of the mechanisms controlling this biomass, its role in the preservation of biodiversity and its influence on climate as well as management tools able to weigh the costs and benefits of exploitation of this community.

In recent years new biological and physical controls have been suggested to drive phytoplankton bloom dynamics in the North Atlantic. A better understanding of the mechanisms driving primary production has potentially important implications for the understanding of the biological carbon pump, as it has for prediction of the system in climate change scenarios. However the scientific discussion regarding this topic has generally failed to integrate the different drivers into a coherent picture, often rendering the proposed mechanisms exclusive to each other. We feel that the suggested mechanisms are not mutually exclusive, but rather complementary. Thus, moving beyond the 'single mechanism' point of view, here we present an integrated conceptual model of the physical and biological controls on phytoplankton dynamics in the North Atlantic. Further we believe that the acclimation of physiological rates can play an important role in mediating phytoplankton dynamics. Thus, this view emphasizes the occurrence of multiple controls and relates their variations in impact to climate change.