Machine learning enables improved runtime and precision for bio-loggers on seabirds

Joseph Korpela,Junichi Nakai,Takuya Maekawa,Masaki Samejima,Hirokazu Suzuki,Yuichi Mizutani,Sakiko Matsumoto,Ken Yoda

doi:10.1038/s42003-020-01356-8

Joseph Korpela, Junichi Nakai + Show 6 more

Open Access

https://doi.org/10.1038/s42003-020-01356-8

Copy DOI

Abstract

Unravelling the secrets of wild animals is one of the biggest challenges in ecology, with bio-logging (i.e., the use of animal-borne loggers or bio-loggers) playing a pivotal role in tackling this challenge. Bio-logging allows us to observe many aspects of animals’ lives, including their behaviours, physiology, social interactions, and external environment. However, bio-loggers have short runtimes when collecting data from resource-intensive (high-cost) sensors. This study proposes using AI on board video-loggers in order to use low-cost sensors (e.g., accelerometers) to automatically detect and record complex target behaviours that are of interest, reserving their devices’ limited resources for just those moments. We demonstrate our method on bio-loggers attached to seabirds including gulls and shearwaters, where it captured target videos with 15 times the precision of a baseline periodic-sampling method. Our work will provide motivation for more widespread adoption of AI in bio-loggers, helping us to shed light onto until now hidden aspects of animals’ lives.

Highlights

Unravelling the secrets of wild animals is one of the biggest challenges in ecology, with biologging playing a pivotal role in tackling this challenge
The bio-logger pictured in Fig. 1a can detect foraging activity using acceleration data (Fig. 1c) in order to extend its runtime by only recording video during periods of that activity, which are indicated by the green segments shown in Fig. 1d, allowing it to capture target behaviours such as those pictured in Fig. 1e, f
We evaluated the effectiveness of our method by using AI on Animals (AIoA)-based camera control on board ten bio-loggers (Supplementary Fig. 1) that were attached to blacktailed gulls from a colony located on Kabushima Island near Hachinohe City, Japan[18], with the AI trained to detect possible foraging behaviour based on acceleration data

Summary

Introduction

Unravelling the secrets of wild animals is one of the biggest challenges in ecology, with biologging (i.e., the use of animal-borne loggers or bio-loggers) playing a pivotal role in tackling this challenge. There have been extraordinary improvements in the sensors and storage capacities of bio-loggers since the first logger was attached to a Weddell seal[4,5,6,7,8,9], their data collection strategies have remained relatively simple: record data continuously, record data in bursts (e.g., periodic sampling), or use manually determined thresholds to detect basic collection criteria such as a minimum depth, acceleration threshold, or illumination level[10,11,12,13,14,15,16,17] These data collection strategies fall short when attempting to collect data using resource-intensive sensors (e.g., video cameras) from specific animal behaviours, as they tend to deplete all of the bio-loggers’ resources on non-target behaviours[18,19]. They include an integrated video camera (high-cost sensor) along with several low-cost sensors including an accelerometer and GPS unit

Methods

Results

Conclusion