The use of technologies in monitoring livestock welfare on-farm

11 Feb 2020

The use of technologies in monitoring livestock welfare on-farm

The Age of Information

There is no shying away from the fact that we live in the Age of Information. Our smartphones alone provide us with inbuilt sat navs, on-tap entertainment, a way to maintain contact with friends and family and strike up conversations with people anywhere in the world. We can bank, shop, and find an answer to almost any question all with minimum effort and input. We’ve become so used to information at our fingertips, that it's easy to forget how we ever got on without it.

Technology for animal welfare

Technology too is now being harnessed in the study of animal behaviour and welfare, the area of research in which I work. Over the past few decades innovation has boomed, and academics and industry alike have ploughed time, effort and money into developing devices and software which not only aid animal production, but which improve welfare.

Prime examples of technological innovation come from animal nutrition. Automatic feeders and drinkers are becoming more and more common and can assist farmers in knowing how much feed and water an individual animal has consumed. As well as being of economic benefit for calculating metrics such as feed conversion, this information may also be used to alert farmers when an animal isn’t following its normal pattern of behaviour, suggesting there may be a problem.

In addition to the basics of feed and water intake, monitoring animal movement patterns is key to detecting abnormal behaviour in groups. We know for ourselves that if we feel unwell, we’re likely to want to rest and be less active than usual and that can applied to other animals. Tracking systems for livestock can use camera-based approaches, RFID tags, accelerometers and GPS locators and have been developed for poultry (Ali and Siegford, 2018), beef and dairy cattle (Awad, 2016) and pigs (Zhang et al., 2019). These systems can track groups or individuals to gain understanding of activity and behaviour and can be useful in predicting key events such as calving (e.g. Borchers et al., 2017) and even future infectious disease in a flock (Colles et al., 2016). The challenges for technology come when we move to situations where there are multiple potential behavioural responses. For example, when humans are in a high stress situation we might have one of several reactions. We may pace or become agitated, we may distract ourselves with another task or become completely removed from the situation. To tackle these challenges, we need to understand an animal’s reaction to a stressful situation in order to correctly train technologies to detect them.

On top of the broad categories of feeding, movement and disease, tech solutions have also been proposed for more specific problems. For example, there are camera systems to predict pig tail-biting onset using the same type of 3D camera technology that Xbox systems use to detect a players’ movements as they participate in a game (D’Eath et al., 2018). Facial recognition technologies are also being developed for pigs, to identify individuals within a pen (Hansen et al., 2018). Odours and levels of ammonia in farm sheds can be monitored using remote sensors called electronic noses (Pan et al., 2007) and mastitis can be detected early in dairy cows using thermal imaging (e.g. Colak et al., 2008).

Can it be relied upon?

Your computer crashes halfway through an important save, flickers back to an old version of the document and hours of work are lost. Technology can fail and we’ve all been there. Just as human error occurs, so too does computer failure. If this is the case, how heavily should we rely on sensors and software to monitor livestock? Most tech solutions are developed not to replace stock people but to enhance what can be done. For example, technology allows for 24/7 monitoring which would be neither practical nor desirable in person.  It extends the reach of capability without removing the need for humans to still be there to make the fundamental decisions that keeps things healthy and productive. Of course, it is extremely beneficial to collect a range of animal- and environment-based data, but those data only become meaningful as information when interpreted by a human. Human management has been, and should remain, key to effective animal production.

Like the distant memory of a Nokia 3310, whether we get to a point at which we barely remember the farming practices of 20 years ago is yet to be seen, but technologies for monitoring animal welfare are certainly becoming more prevalent. These advances are important innovations for current and future animal production and should be used as one tool in our kit to aid healthy and efficient production.


Ali, A., & Siegford, J. (2018). An approach for tracking directional activity of individual laying hens within a multi-tier cage-free housing system (aviary) using accelerometers. In Measuring behaviour 2018.

Awad, A. I. (2016). From classical methods to animal biometrics: A review on cattle identification and tracking. Computers and Electronics in Agriculture.

Borchers, M. R., Chang, Y. M., Proudfoot, K. L., Wadsworth, B. A., Stone, A. E., & Bewley, J. M. (2017). Machine-learning-based calving prediction from activity, lying, and ruminating behaviors in dairy cattle. Journal of Dairy Science.

Colak, A., Polat, B., Okumus, Z., Kaya, M., Yanmaz, L. E., & Hayirli, A. (2008). Short communication: Early detection of mastitis using infrared thermography in dairy cows. Journal of Dairy Science.

Colles, F. M., Cain, R. J., Nickson, T., Smith, A. L., Roberts, S. J., Maiden, M. C. J., … Dawkins, M. S. (2016). Monitoring chicken flock behaviour provides early warning of infection by human pathogen Campylobacter. Proceedings of the Royal Society B: Biological Sciences, 283(1822), 20152323.

D’Eath, R. B., Jack, M., Futro, A., Talbot, D., Zhu, Q., Barclay, D., & Baxter, E. M. (2018). Automatic early warning of tail biting in pigs: 3D cameras can detect lowered tail posture before an outbreak. PLoS ONE, 13(4), 1–18.

Hansen, M. F., Smith, M. L., Smith, L. N., Salter, M. G., Baxter, E. M., Farish, M., & Grieve, B. (2018). Towards on-farm pig face recognition using convolutional neural networks. Computers in Industry.

Pan, L., Yang, S. X., Pan, L., & Yang, · S X. (2007). A new intelligent electronic nose system for measuring and analysing livestock and poultry farm odours. Environ Monit Assess, 135, 399–408.

Zhang, L., Gray, H., Ye, X., Collins, L., & Allinson, N. (2019). Automatic individual pig detection and tracking in pig farms. Sensors (Switzerland), 19(5).


By Helen Gray