Automatic classification of field-collected dinoflagellates by artificial neural network

Automatic taxonomic categorisation of 23 species of dinoflagellates was demonstrated using field-collected specimens. These dinoflagellates have been responsible for the majority of toxic and noxious phytoplankton blooms which have occurred in the coastal waters of the European Union in recent years and make severe impact on the aquaculture industry. The performance by human 'expert' ecologists/taxonomists in identifying these species was compared to that achieved by 2 artificial neural network classifiers (multilayer perceptron and radial basis function networks) and 2 other statistical techniques, k-Nearest Neighbour and Quadratic Discriminant Analysis. The neural network classifiers outperform the classical statistical techniques. Over extended trials, the human experts averaged 85% while the radial basis network achieved a best performance of 83%, the multilayer perceptron 66%, k-Nearest Neighbour 60%, and the Quadratic Discriminant Analysis 56%.

Diet of auklet chicks in the Aleutian Islands, Alaska: similarity among islands, interspecies overlap, and relationships to ocean climate

Seabirds are effective samplers of the marine environment, and can be used to measure resource partitioning among species and sites via food loads destined for chicks. We examined the composition, overlap, and relationships to changing climate and oceanography of 3,216 food loads from Least, Crested, and Whiskered Auklets (Aethia pusilla, A. cristatella, A. pygmaea) breeding in Alaska during 1994–2006. Meals comprised calanoid copepods (Neocalanus spp.) and euphausiids (Thysanoessa spp.) that reflect secondary marine productivity, with no difference among Buldir, Kiska, and Kasatochi islands across 585 km of the Aleutian Islands. Meals were very similar among species (mean Least–Crested Auklet overlap C = 0.68; Least–Whiskered Auklet overlap C = 0.96) and among sites, indicating limited partitioning of prey resources for auklets feeding chicks. The biomass of copepods and euphausiids in Least and Crested Auklet food loads was related negatively to the summer (June–July–August) North Pacific Gyre Oscillation, while in Whiskered Auklet food loads, this was negatively related to the winter (December–January–February) Pacific Decadal Oscillation, both of which track basin-wide sea-surface temperature (SST) anomalies. We found a significant quadratic relationship between the biomass of calanoid copepods in Least Auklet food loads at all three study sites and summer (June–July) SST, with maximal copepod biomass between 3–6°C (r 2 = 0.71). Outside this temperature range, zooplankton becomes less available to auklets through delayed development. Overall, our results suggest that auklets are able to buffer climate-mediated bottom-up forcing of demographic parameters like productivity, as the composition of chick meals has remained constant over the course of our study.