Phenomics

Estrus Detection from Ear Tag Accelorometry in Grazing Cattle

---

Abstract

Timely and accurate detection of estrus is essential for improving cattle reproductive efficiency and herd management. We present a lightweight, data-driven pipeline that infers estrus from daily behavior patterns captured by ear-tag triaxial accelerometer data. At its core is a compact deep learning model that estimates per-animal daily behavior profiles from raw accelerometry. To account for individual and temporal variation, we compute individualized baseline profiles via causal dynamic trimmed means over preceding days and express features as deviations of daily behavior durations from these baselines. We fit a binary regularized logistic regression model to these features for final estrus detection. Evaluated on data from 33 Angus cows fitted with smart ear-tags during a four-month grazing trial in temperate Australia, the approach delivers high discriminative performance at an ultra-low computational footprint. The results confirm that subtle yet systematic behavioral deviations, measured by low-cost accelerometers, are reliable predictors of estrus, directly enabling scalable, infrastructure-light, and autonomous reproductive monitoringin extensive grazing systems. Crucially, the pipeline is compatible with on-tag or edge deployment and integrates readily with existing digital-agriculture workflows for alerting and decision support.

Keywords: 2026

How to Cite:

White, S. & Campbell, G., (2026) “Estrus Detection from Ear Tag Accelorometry in Grazing Cattle”, World Congress on Genetics Applied to Livestock Production Digital Archive 2026(1): 2286136. doi: https://doi.org/10.31274/wcgalp.23860

Rights: 1