Project

Monitoring predictive indicators of stressors in laying hens

Traditionally, laying hen farmers monitor health, welfare and productivity of their flock based on feed and water intake of the birds, several climate factors, the productive output of the flock (egg production and bird weight) and observations on behavioral performance. Due to the growing number of birds per layer farm and the decreased availability of qualified personnel, it becomes increasingly difficult to safeguard and control animal health and welfare. Concurrently, there is a global trend towards more sustainable livestock farming with profitable animal production and efficiency, maintaining good animal health and welfare and food safety and a low ecological footprint. To keep up with these developments, farmers can benefit from state-of-the art sensor technology, serving as artificial nose, ears and eyes that gather 24/7 data on flock health, welfare and productivity.

This research project aims to improve laying hen welfare in aviaries by early detection of stressors based on continuous assessment of reliable, (predictive) animal-based indicators. Relevant stressors and their indicators have been identified during interviews with laying hen farmers, poultry vets and other poultry experts. To facilitate objective deviation detection in layer production, an adaptive, dynamic, expert-mediated algorithm has been developed that continuously predicts future egg production and detects deviation in the egg production curve. Moreover, an explorative study has shown that volatile (odor) analysis of manure could pose an opportunity to detect deviations in layer pullet intestinal health on commercial farms.

Currently, we are studying the potential added value of continuously recording vocalizations and spatial behavior with resp. acoustic sensors and cameras in a semi-commercial aviary system for laying hens. Our aim is to detect stressful events based on the sound and behavior of the laying hens. Vocalisations and spatial behavior are processed and analyzed using automatic software tools, and the resulting data are combined with sensor-enabled data on feed and water intake, climate parameters and egg production.

Ultimately, the output from this project can be used to develop a predictive monitoring platform for the poultry farmer, to support farm management decisions and to validate effects of data-driven decisions on laying hen health, welfare and productivity.