Artificial keys for botanical identification using a multilayer perceptron neural network (MLP)

In this paper, practical generation of identification keys for biological taxa using a multilayer perceptron neural network is described. Unlike conventional expert systems, this method does not require an expert for key generation, but is merely based on recordings of observed character states. Like a human taxonomist, its judgement is based on experience, and it is therefore capable of generalized identification of taxa. An initial study involving identification of three species of Iris with greater than 90% confidence is presented here. In addition, the horticulturally significant genus Lithops (Aizoaceae/Mesembryanthemaceae), popular with enthusiasts of succulent plants, is used as a more practical example, because of the difficulty of generation of a conventional key to species, and the existence of a relatively recent monograph. It is demonstrated that such an Artificial Neural Network Key (ANNKEY) can identify more than half (52.9%) of the species in this genus, after training with representative data, even though data for one character is completely missing.

Typification of four North American club-chollas: the names of four Engelmannian species from Mexico and Southwestern United States

The names Opuntia bulbispina, O. clavata, O. emoryi and O. grahamii, originally proposed by George Engelmann between 1848 and 1856, are reviewed and typified after new findings of previously unknown voucher specimens. Original materials collected by some of the collaborators employed by Engelmann during the Mexican Boundary Survey were discovered in a loan from the Torrey Herbarium at the New York Botanical Garden (NY). Many of the materials include fragments of stems and fruits, and others include only sectioned flowers and some seeds. Particularly good descriptions of the species here concerned were published in Engelmann’s “Synopsis of the Cactaceae” in 1857, and exceptional illustrations were produced by Paulus Roetter and printed in “Cactaceae of the Boundary” in 1859. The problems surrounding some previous typifications of these names range from typification of joint lectotypes to illegitimate typifications of illustrations when original material was known to exist. The materials selected for typification were collected by the Mexican Boundary Survey and are lodged at the herbaria of the Missouri Botanical Garden (MO) and the New York Botanical Garden (NY); some are illustrations published by Engelmann.