Identification of New Zealand bats (Chalinolobus tuberculatus and Mystacina tuberculata) in flight from analysis of echolocation calls by artificial neural networks

Time-expanded and heterodyned echolocation calls of the New Zealand long-ta iled Chalinolobus tuberculatus and lesser short-tailed bat Mystacina tuberc ulata were recorded and digitally analysed. Temporal and spectral parameter s were measured from time-expanded calls and power spectra generated for bo th time-expanded and heterodyned calls. Artificial neural networks were tra ined to classify the calls of both species using temporal and spectral para meters and power spectra as input data. Networks were then tested using dat a not previously seen. Calls could be unambiguously identified using parame ters and power spectra from time-expanded calls. A neural network, trained and tested using power spectra of calls from both species recorded using a heterodyne detector set to 40 kHz (the frequency with the most energy of th e fundamental of C. tuberculatus call), could identify 99% and 84% of calls of C. tuberculatus and M. tuberculatus, respectively. A second network, tr ained and tested using power spectra of calls from both species recorded us ing a heterodyne detector set to 27 kHz (the frequency with the most energy of the fundamental of M. tuberculata call), could identify 34% and 100% of calls of C. tuberculatus and M. tuberculata, respectively. This study repr esents the first use of neural networks for the identification of bats from their echolocation calls. It is also the first study to use power spectra of time-expanded and heterodyned calls for identification of chiropteran sp ecies. The ability of neural networks to identify bats from their echolocat ion calls is discussed, as is the ecology of both species in relation to th e design of their echolocation calls.