Ecological inference using data from accelerometers needs careful protocols
O_LIAccelerometers in animal-attached tags have proven to be powerful tools in behavioural ecology, being used to determine behaviour and provide proxies for movement-based energy expenditure. Researchers are collecting and archiving data across systems, seasons and device types. However, in order to use data repositories to draw ecological inference, we need to establish the error introduced according to sensor type and position on the study animal and establish protocols for error assessment and minimization. C_LIO_LIUsing laboratory trials, we examine the absolute accuracy of tri-axial accelerometers and determine how inaccuracies impact measurements of dynamic body acceleration (DBA), as the main acceleration-based proxy for energy expenditure. We then examine how tag type and placement affect the acceleration signal in birds using (i) pigeons Columba livia flying in a wind tunnel, with tags mounted simultaneously in two positions, (ii) back- and tail-mounted tags deployed on wild kittiwakes Rissa tridactyla. Finally, we (iii) present a case study where two generations of tag were deployed using different attachment procedures on red-tailed tropicbirds Phaethon rubricauda foraging in different seasons. C_LIO_LIBench tests showed that individual acceleration axes required a two-level correction (representing up to 4.3% of the total value) to eliminate measurement error. This resulted in DBA differences of up to 5% between calibrated and uncalibrated tags for humans walking at different speeds. Device position was associated with greater variation in DBA, with upper- and lower back-mounted tags in pigeons varying by 9%, and tail- and back-mounted tags varying by 13% in kittiwakes. Finally, DBA varied by 25% in tropicbirds between seasons, which may be attributable to tag attachment procedures. C_LIO_LIAccelerometer accuracy, tag placement, and attachment details critically affect the signal amplitude and thereby the ability of the system to detect biologically meaningful phenomena. We propose a simple method to calibrate accelerometers that should be used prior to deployments and archived with resulting data, suggest a way that researchers can assess accuracy in previously collected data, and caution that variable tag placement and attachment can increase sensor noise and even generate trends that have no biological meaning. C_LI