| Autor: |
Amorós-Ausina D; Urbanización Maryvilla, 03710 Calpe, Spain., Schuchmann KL; Computational Bioacoustics Research Unit (CO.BRA), Institute for Science and Technology in Wetlands (INAU), Federal University of Mato Grosso (UFMT), Cuiabá 78060-900, Brazil.; Ornithology, Zoological Research Museum A. Koenig (ZFMK), 53113 Bonn, Germany.; Postgraduate Program in Zoology, Institute of Biosciences, Federal University of Mato Grosso, Cuiabá 78060-900, Brazil., Marques MI; Computational Bioacoustics Research Unit (CO.BRA), Institute for Science and Technology in Wetlands (INAU), Federal University of Mato Grosso (UFMT), Cuiabá 78060-900, Brazil.; Postgraduate Program in Zoology, Institute of Biosciences, Federal University of Mato Grosso, Cuiabá 78060-900, Brazil., Pérez-Granados C; Computational Bioacoustics Research Unit (CO.BRA), Institute for Science and Technology in Wetlands (INAU), Federal University of Mato Grosso (UFMT), Cuiabá 78060-900, Brazil.; Conservation Biology Group, Landscape Dynamics and Biodiversity Programme, Forest Science and Technology Center of Catalonia (CTFC), 25280 Lleida, Spain.; Ecology Department, Alicante University, 03080 Alicante, Spain. |
| Abstrakt: |
In recent years, several automated and noninvasive methods for wildlife monitoring, such as passive acoustic monitoring (PAM), have emerged. PAM consists of the use of acoustic sensors followed by sound interpretation to obtain ecological information about certain species. One challenge associated with PAM is the generation of a significant amount of data, which often requires the use of machine learning tools for automated recognition. Here, we couple PAM with BirdNET, a free-to-use sound algorithm to assess, for the first time, the precision of BirdNET in predicting three tropical songbirds and to describe their patterns of vocal activity over a year in the Brazilian Pantanal. The precision of the BirdNET method was high for all three species (ranging from 72 to 84%). We were able to describe the vocal activity patterns of two of the species, the Buff-breasted Wren ( Cantorchilus leucotis ) and Thrush-like Wren ( Campylorhynchus turdinus ). Both species presented very similar vocal activity patterns during the day, with a maximum around sunrise, and throughout the year, with peak vocal activity occurring between April and June, when food availability for insectivorous species may be high. Further research should improve our knowledge regarding the ability of coupling PAM with BirdNET for monitoring a wider range of tropical species. |
