AI that can detect baby chickens’ distress signals is being developed by scientists.

Artificial intelligence (AI) that can automatically recognise and tally chicken distress signals has been created by scientists. According to them, farmers will be able to preserve the lives of these birds within five years of the new technology becoming available.

Researchers assert that the AI can accurately identify distress sounds from other barn noises with 97% accuracy. The AI recognises and quantifies distress calls emitted by chickens housed in enormous indoor sheds.

Young chicks make distress sounds, which are high-pitched, repeating chirps, to get their mother hen’s attention when they need food or are in trouble. However, it might be challenging to determine when a chicken is uncomfortable, socially isolated, or hungry in a commercial chicken farm. It may be the difference between life and death to answer these calls.

Researchers from City University of Hong Kong recorded the vocalisations of chickens housed at Lingfeng Poultry Ltd., a significant poultry producer in China’s Guangxi province, in order to advance these efforts.

There were roughly 2000–2500 chickens kept in each barn in stacked cages (three cages per stack, 13–20 individuals each cage).

Over the course of a year, the researchers recorded the surroundings, capturing sounds ranging from chick distress calls to natural farm sounds like employees hosing out barn floors.

All of these noises were then converted into spectrograms, which are sound images, and the images were used to train a specific kind of AI algorithm known as deep learning.

‘Chickens are very vocal, but the distress call tends to be louder than the others, and is what we would describe as a pure tonal call,’ The Guardian quoted Alan McElligott, an associate professor of animal behaviour and welfare at the City University of Hong Kong.

‘Even to the untrained ear, it’s not too difficult to pick them out.’