ARPHA Conference Abstracts : Conference Abstract
PDF
Conference Abstract
Developing a novel bioacoustic monitoring for Garden Dormice using passive sound recorders and machine learning
expand article infoSarah Thivierge‡,§, Robin Sandfort|, Holger U. Meinig, Livia Schäffler§, Johannes Lang
‡ University of Bonn, Regina-Pacis-Weg 3, D-53113, Bonn, Germany
§ Leibniz Institute for the Analysis of Biodiversity Change, Zoological Research Museum Alexander Koenig, Center for Biodiversity Monitoring, section Conservation Ecology, Adenauerallee 160 (mailing adress 127), D-53113, Bonn, Germany
| capreolus e.U. and University of Natural Resources and Life Sciences, Vienna (BOKU), Department of Integrative Biology and Biodiversity Research, Institute of Wildlife Biology and Game Management, Orth an der Donau, Austria
¶ Justus-Liebig-University Giessen, Clinic for birds, reptiles, amphibians and fish, Working Group for Wildlife Research, Frankfurter Strasse 114, D-35392, Giessen, Germany
Corresponding author: Sarah Thivierge (sarah.thivierge80@gmail.com)
Received: 29 Mar 2022 | Published: 15 Apr 2022
© 2022 Sarah Thivierge, Robin Sandfort, Holger Meinig, Livia Schäffler, Johannes Lang
This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Citation: Thivierge S, Sandfort R, Meinig HU, Schäffler L, Lang J (2022) Developing a novel bioacoustic monitoring for Garden Dormice using passive sound recorders and machine learning. ARPHA Conference Abstracts 5: e84574. https://doi.org/10.3897/aca.5.e84574
 Open Access

Abstract

One of the challenges of small mammal conservation is to be able to find the target species in the field. This is especially true for small nocturnal hibernators like dormice. Passive bioacoustic monitoring, as a non-invasive method, can be a useful tool to more efficiently find vocalizing animals in the field. However, bioacoustic methods produce a large amount of data, of which the manual analysis is highly time consuming. Therefore, there is need for an automatized process for identifying animal vocalization in acoustic data. Two types of recorders, audiomoths and BAR-LT recorders, were installed at a total of 10 locations of known Garden Dormouse (Eliomys quercinus) activity in Germany and were left recording in the field from June to September, producing a total of 3.54 TB of data. Based on our own and volunteers’ observations, Garden Dormouse vocalizations were manually identified in a subset of the sound files produced. These vocalizations, as well as ambient sound samples, were labelled and extracted to train a TensorFlow model, which was then tested on new subsets of the complete dataset. Comparing sound quality and acquisition costs of the two recorder types shows the potential for large-scale monitoring applications using the less expensive and open source audiomoth. Next steps include a time analysis of Garden Dormouse calls to find out when they are vocally more active during the study period. Such knowledge can help narrow the temporal scale of future bioacoustic studies on this species.

Keywords

In Search of the Garden Dormouse, conservation, small mammals, vocalization, animal communication

Presenting author

Sarah Thivierge

Presented at

Poster presented at the 11th International Dormouse Conference (May 9-13, 2022)

Funding program

This project is/was funded by the German Federal Agency for Nature Conservation with resources from the German Federal Ministry for the Environment, Nature Conservation, Nuclear Safety and Consumer Protection.

login to comment