Abstract
Geolocators are a well-established technology to reconstruct migration routes of animals that are too small to carry satellite tags (e.g. passerine birds). These devices record environmental light-level data that enable the reconstruction of daily positions from the time of twilight. However, all current methods for analysing geolocator data require manual pre-processing of raw records to eliminate twilight events showing unnatural variation in light levels, a step that is time-consuming and must be accomplished by a trained expert. Here, we propose and implement advanced machine learning techniques to automate this procedure and we apply them to 108 migration tracks of barn swallows ( Hirundo rustica). We show that routes reconstructed from the automated pre-processing are comparable to those obtained from manual selection accomplished by a human expert. This raises the possibility of fully automating light-level geolocator data analysis and possibly analysing the large amount of data already collected on several species.
Highlights
Recent decades have been characterized by environmental and climatic changes that occur on the global scale [1]
The confusion matrix for the three machine learning (ML) models used in this study revealed that the performances obtained in the three phases of the model calibration were nearly the same
Beyond comparing the classifications of twilights performed by our different ML algorithms, we aimed to assess whether ML can provide a reliable pre-filtering of twilight data for reconstructing migration routes of animals
Summary
Recent decades have been characterized by environmental and climatic changes that occur on the global scale [1]. Migratory animals are considered sensitive to global changes because they should adjust their life cycle to changes that occur at different rates in areas that are separated by long distances [3,4]. It is, important to understand if and how the movement pattern of longdistance migratory species is affected by climate and environmental change. The continuous development of new devices—which allow monitoring, recording and sometimes transmitting the positions of individuals over long time periods and large spatial extents—opens novel research perspectives that must be accompanied by advanced ways of interpreting the newly available data through proper modelling and software
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
