Evaluation of acoustic pattern recognition of nightingale (Luscinia megarhynchos) recordings by citizens

Acoustic pattern recognition methods introduce new perspectives for species identification, biodiversity monitoring and data validation in citizen science but are rarely evaluated in real world scenarios. In this case study we analysed the performance of a machine learning algorithm for automated bird identification to reliably identify common nightingales (Luscinia megarhynchos) in field recordings taken by users of the smartphone app Naturblick. We found that the performance of the automated identification tool was overall robust in our selected recordings. Although most of the recordings had a relatively low confidence score, a large proportion of the recordings were identified correctly.

Population expansion of some bird species in the city of Wrocław

During the years 2002-2010, distribution and numbers of eight bird species were studied in the whole city of Wrocław, SW Poland (293 km2). The estimation for these species are as follow: Streptopelia turtur: 3 breeding pairs, Upupa epops: 1, Cuculus canorus: 49, Emberiza hortulana: 7, Luscinia megarhynchos: 214-286, Phoenicurus phoenicurus: 87-118, Turdus pilaris: 105-150, Hippolais icterina: 136-181. In comparison with 1980‘s and 1990’s, a rapid increase in the numbers P. phoenicurus, and T. pilaris, and a slight increase of L. megarhynchos and Cuculus canorus were documented. T. pilaris began to breed in the city in the end of 1990‘s. The increase may indicate that the habitats in Wrocław improved both in regard to food availability, nesting sites and other environmental requisitions. The increase in the numbers recorded for C. canorus, P. phoe-nicurus, and L. megarhynchos may also be a result of good conditions prevailing in their wintering grounds in sub-Saharan Africa.