Application of machine learning and acoustic predation tags to classify migration fate of Atlantic salmon smolts

Abstract

Mortality and predation of tagged shes presents a serious challenge to interpreting results of acoustic telemetry studies. There is a need for standardized methods to identify predated individuals and reduce the impacts of "predation bias" on results and conclusions. Here, we use emerging approaches in machine learning and acoustic tag technology to classify out-migrating Atlantic salmon (Salmo salar) smolts into different fate categories. We compared three methods of fate classi cation; predation tag pH sensors and detection data, unsupervised k-means clustering, and supervised random forest combined with tag pH sensor data. Random forest models increased predation estimates by 9-32% compared to pH sensor data, while clustering reduced estimates by 3.5-30%. The greatest changes in estimates were seen in years with large class imbalance or low model accuracy. Both supervised and unsupervised approaches were able to classify smolt fate, however, in-sample model accuracy improved when using tag sensor data to train models, emphasizing the value of incorporating such sensors when studying predator-prone sh. Sensor data may not be su cient to identify predation in isolation due to Type I and Type II error in predation sensor triggering. Combining sensor data with machine learning approaches should be standard practice to more accurately classify fate of tagged sh. Highlighted Student PaperThis paper contributes signi cantly to the eld of ecology by introducing a standardized work ow for analyzing telemetry data which is greatly needed to reduce biases in study results.

Effects of handling and surgical implant on juvenile wild trout: Physiological and behavioral impact

“…Consequently, these factors could lead to modifications in fish physiological and behavioral parameters, significantly affecting the overall health, particularly in early-life fish populations. Additionally, predatory species relying on speed for prey capture may experience reduced success rates and hindered growth, whereas for migrating species, changes in swimming performance could lead to delays or reductions in migration success (Notte et al, 2022).…”

Estimating predation rates of stocked juvenile Chinook Salmon using novel acoustic predation transmitters

“…These transmitters have a unique sensor that triggers a change in tag transmission as predator digestive enzymes break down a polymer coating (Halfyard et al 2017). Most tests of this technology to date have occurred in laboratory or captive settings (Halfyard et al 2017;Lennox et al 2021), but more recent research has implemented these transmitters in the wild (Klinard et al 2019;Weinz et al 2020;Notte et al 2022). Weinz et al (2020) observed predation triggers on 32% of tagged Yellow Perch Perca flavescens and changes in movement patterns of tagged fish aligned with transmitter-identified predation events.…”