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.

Marine biodiversity and climate change: assessing and predicting the influence of climatic change using intertidal rocky shore biota. Occasional Publication of the Marine Biological Association 20

In the last 60 years climate change has altered the distribution and abundance of many seashore species. Below is a summary of the findings of this project. The MarClim project was a four year multi-partner funded project created to investigate the effects of climatic warming on marine biodiversity. In particular the project aimed to use intertidal species, whose abundances had been shown to fluctuate with changes in climatic conditions, as indicator species of likely responses of species not only on rocky shores, but also those found offshore. The project used historic time series data, from in some cases the 1950s onwards, and contemporary data collected as part of the MarClim project (2001-2005), to provide evidence of changes in the abundance, range and population structure of intertidal species and relate these changes to recent rapid climatic warming. In particular quantitative counts of barnacles, limpets and trochids were made as well as semi-quantitative surveys of up to 56 intertidal taxa.Historic and contemporary data informed experiments to understand the mechanisms behind these changes and models to predict future species ranges and abundances.

Data rescue and re-use: Recycling old information to address new policy concerns

Information on past trends is essential to inform future predictions and underpin attribution needed to drive policy responses. It has long been recognised that sustained observations are essential for disentangling climate-driven change from other regional and local-scale anthropogenic impacts and environmental fluctuations or cycles in natural systems. This paper highlights how data rescue and re-use have contributed to the debate on climate change responses of marine biodiversity and ecosystems. It also illustrates via two case studies the re-use of old data to address new policy concerns. The case studies focus on (1) plankton, fish and benthos from the Western English Channel and (2) broad-scale and long-term studies of intertidal species around the British Isles. Case study 1 using the Marine Biological Association of the UK's English Channel data has shown the influence of climatic fluctuations on phenology (migration and breeding patterns) and has also helped to disentangle responses to fishing pressure from those driven by climate, and provided insights into ecosystem-level change in the English Channel. Case study 2 has shown recent range extensions, increases of abundance and changes in phenology (breeding patterns) of southern, warm-water intertidal species in relation to recent rapid climate change and fluctuations in northern and southern barnacle species, enabling modelling and prediction of future states. The case is made for continuing targeted sustained observations and their importance for marine management and policy development.

Macroscale factors affecting diatom abundance: a synergistic use of Continuous Plankton Recorder and satellite remote sensing data

Diatoms exist in almost every aquatic regime; they are responsible for 20% of global carbon fixation and 25% of global primary production, and are regarded as a key food for copepods, which are subsequently consumed by larger predators such as fish and marine mammals. A decreasing abundance and a vulnerability to climatic change in the North Atlantic Ocean have been reported in the literature. In the present work, a data matrix composed of concurrent satellite remote sensing and Continuous Plankton Recorder (CPR) in situ measurements was collated for the same spatial and temporal coverage in the Northeast Atlantic. Artificial neural networks (ANNs) were applied to recognize and learn the complex non-monotonic and non-linear relationships between diatom abundance and spatiotemporal environmental factors. Because of their ability to mimic non-linear systems, ANNs proved far more effective in modelling the diatom distribution in the marine ecosystem. The results of this study reveal that diatoms have a regular seasonal cycle, with their abundance most strongly influenced by sea surface temperature (SST) and light intensity. The models indicate that extreme positive SSTs decrease diatom abundances regardless of other climatic conditions. These results provide information on the ecology of diatoms that may advance our understanding of the potential response of diatoms to climatic change.