Within the framework of the Bird Audio Detection challenge, the research team was able to train artificial intelligence to recognize birds by their singing. A new function will help to correctly calculate the aureole of birds of one species or another in different parts of the world. This is important for tracking the trend towards the extinction of birds and taking measures to conserve populations in certain regions, which is important, given the extent of deforestation, agriculture and climate change trends. In the process, experts involved 30 machine-based programs that were practiced on records birds singing from the exclusion zone of the Chernobyl nuclear power plant. A large variety of birds is concentrated in this vast, quiet territory, and their sounds are not distorted and do not mix with the roar of human activity – the voices of people, the city, the sounds of cars, factories and other things. During the tests, artificial intelligence showed a recognition accuracy of 89%. While AI is not able to surpass the capabilities of ornithologists who can distinguish birds from singing, the neural network can be used anywhere in the world, and it is not against rain or work around the clock. But it is likely that after some time, AI will be able to boast a better result than that of specialists. If only the birds continued to exist in their natural habitat, and not in cages.