Abstract
BACKGROUND: The yellow-legged hornet (Vespa velutina) is native to Southeast Asia and is an invasive alien species of concern in many countries. More effective management of populations of V. velutina could be achieved through more widespread and intensive monitoring in the field, however current methods are labor intensive and costly. To address this issue, we have assessed the performance of an optical sensor combined with a machine learning model to classify V. velutina and native wasps/hornets and bees. Our aim is to use the results of the present work as a step towards the development of a monitoring solution for V. velutina in the field. RESULTS: We recorded a total 935 flights from three bee species: Apis mellifera, Bombus terrestris and Osmia bicornis; and four wasp/hornet species: Polistes dominula, Vespula germanica, Vespa crabro and V. velutina. The machine learning model achieved an average accuracy for species classification of 80.1 ± 13.9% and 74.5 ± 7.0% for V. velutina. V. crabro had the highest level of misclassification, confused mainly with V. velutina and P. dominula. These results were obtained using a 14-value peak and valley feature derived from the wingbeat power spectral density. CONCLUSION: This study demonstrates that the wingbeat recordings from a flying insect sensor can be used with machine learning methods to differentiate V. velutina from six other Hymenoptera species in the laboratory and this knowledge could be used to help develop a tool for use in integrated invasive alien species management programs. © 2022 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.