NEURAL-NETWORK ANALYSIS OF FLOW CYTOMETRIC DATA FOR 40 MARINE-PHYTOPLANKTON SPECIES

Flow cytometry data (time of flight, horizontal and vertical forward light scatter, 90-degrees light scatter, and ''red'' and ''orange'' integral fluorescence) were collected for laboratory cultures of 40 species of marine phytoplankton, from the following taxonomic classes, the Dinophyceae, Bacillariophyceae, Prymnesiophyceae, Cryptophyceae, and other flagellates. Single-hidden-layer ''back-propagation'' neural networks were trained to discriminate between species by recognising patterns in their flow cytometric signatures, and network performance was assessed using an independent test data set. Two approaches were adopted employing: (1) a hierarchy of small networks, the first identifying to which major taxonomic group a cell belonged, and then a network for that taxonomic group identified to species, and (2) a single large network. Discriminating some of the major taxonomic groups was successful but others less so. With networks for specific groups, cryptophyte species were all identified reliably (probability of correct classification always being > 0.75); in the other groups half of the species were identified reliably. With the large network, dinoflagellates, cryptomonads, and flagellates were identified almost as well as by networks specific for these groups. The application of neural computing techniques to identification of such a large number of species represents a significant advance from earlier studies, although further development is required. (C) 1994 Wiley-Liss, Inc.