MULTI-SENSOR FEEDER: AUTOMATED AND EASY-TO-USE BIRDS MONITORING TOOL FOR CITIZENS
Keywords: Citizen Science, Species Distribution, Image Recognition, Biodiversity Monitoring, Do-It-Yourself, Artificial Intelligence, Open Science, Reproducibility
Abstract. Nowadays, more species are threatened with extinction than ever before in the human era. Especially breeding birds are considered endangered. At the same time, it is difficult to obtain sufficient data not only to raise awareness for this situation, but also to gain a better understanding and to develop potential countermeasures. We show how a citizen science based biodiversity monitoring for birds, using an automated and easy-to-use multi-sensor feeder, can look like. In doing so, we compare different configuration options concerning technical components, casing, as well as software to be used and present our suggested prototype: A smart bird feeder including an environmental sensor, a microphone, as well as a balance and a camera in a wooden case. It identifies the type of visiting birds using AI and publishes the recognized species, including all further collected data, on an open access website. The station can be reproduced by anyone at an affordable price in a Do-It-Yourself format, making citizens a key contributor to biodiversity monitoring.