“Its motion was so swift, complex and perfect that at first I did not see it as a machine”. Written over 125 years ago, these immortal words of HG Wells are as real today as in the turbulent era of their Victorian author. While these words were penned at a time of great mechanical development, with the awe and might of industrialised humanity (and with the mechanisation of warfare at the time), they spoke of an age where “machines” would dominate all of human existence.
There can be no more controversial interface between technology and the health and welfare of the animals who produce our food; in the same way that Wells used the machines in The War of the Worlds to question Western Imperialism, should we be questioning the relationship between animals who produce our food and our reliance on technology to rear them?
The story of political change
Ten years ago, in 2013 the UK Government, under the 2010-2015 Conservative and Liberal Democrat coalition, released a statement claiming the UK would become a world leader in agricultural science and technology, following the launch of the Agricultural Technologies strategy. The aim was to deliver sustainable, healthy and affordable food for future generations. Little did they know at the time that a referendum in 2016 would see the UK move away from the European Union.
‘Brexit’ posed some additional challenges to technological progress in UK agriculture and farming. With the withdrawal from the EU, UK farmers have lost payments under the EU’s common agricultural policy (CAP). For many, these are vital to business sustainability and provide the “lump sum of capital” that provides the annual opportunity to channel money into their farming businesses’ technological advancement. But others saw these payments as barriers to progress, encouraging the status quo and entrenching traditional farming methods. They hoped for an unsubsidised ‘free market’ approach, which would encourage a new efficiency in domestic production. In 2018, UK farmers received around £3.5 billion per year in CAP payments, in many ways an indirect support for our diverse rural economy, keeping sheep on the fells and cattle on the meadows.
In recent years, the Agriculture Act, passed in November 2020, set out a new legislative framework for a new subsidy regime in England – hoping to lessen the impact of the loss of EU subsidies and set the agenda for a new agricultural evolution. Aiming to encourage land stewardship, production efficiency and animal welfare, the strategy endeavours to achieve public goods from public funds. For agri-tech this policy has a clear aim: to support the adoption of new technology on UK farms, which have been falling behind both our European neighbours and our global competitors in production efficiency.
Since the Government statement in 2013, the UK farming and agriculture sector has changed massively, with some of this progress driven by an increase in investment in agricultural science and tech. But has this been enough? The ‘peak’ in this investment was 2021, where the UK saw £1.3 billion in agri-tech deals – showing a strong trend for interest in viable solutions to the challenges facing UK agriculture such as food security, environmental impact and sustainability, improved animal health and welfare and rising input costs. To improve productivity, efficiency, sustainability, profitability, quality and welfare, agri-tech investment has become the 15th fastest-growing sector in the UK. And after the recent COP28 declaration on sustainable agriculture, resilient food systems and climate action, surely this will only see the sector leap up the leaderboard?
So how can the agri-tech sector encourage investment and innovation in agricultural technology? Are there any downfalls to these new technologies? And, importantly, what are UK companies doing to alleviate these issues?
Artificial Intelligence
Nothing is more ‘sexy’ at the moment than AI. Artificial intelligence clearly has many applications in science and innovation, but the ‘big problem’ in agriculture is data, where quality is essential. “Ground truth data” – data collected from real world observations – that is objective, free from bias, repeatable and consistent is needed to ‘train’ systems and provide an evidence-based approach. Ensuring that the data that the AI has ‘learnt’ from is of good quality and sound scientific basis allows the information to be of high quality, therefore integrity of the source data is essential.
There are a number of areas where agriculture hits barriers to quality data collection and provision, and the best new companies in the sector ensure data preparation, data processing during model training and data quality monitoring post launch are given the highest priority. This is where data scientists and animal scientists must all work together. Veterinary professionals with a background in medical and clinical interactions, alongside knowledge of animal welfare and the physiology of efficiency, provide another integral link.
But simply training outcomes on human interventions won’t be enough, and AI will need ‘machine learning’ and deep neural networks to ensure the benefits of agri-tech yields the benefits from animal production that our world so desperately needs. Therefore, having an AI model with high sensitivity is important, as with any other test in a medical setting.
Body Condition Technology
Food producers and the agricultural/farming industry currently rely on subjective visual observation, human recording and manual reporting of all the key health and welfare traits, including Body Condition Score (BCS). This clearly has its drawbacks: it is time consuming, subjective, and labour-intensive, with a large margin of error when applied to large scale herd health monitoring. That’s not to say that the people doing so are not highly skilled professionals, but there is inevitable human error, paired with the constraints of busy farm management, which can lead to cases only getting picked up later in their disease process. Looking at the herd ‘day in-day out’ blinds us to the insidious changes of declining outcomes.
For farmers, tracking Body Condition Score (BCS) of their herd can help monitor performance: BCS is a major indicator of metabolic performance in dairy cows and directly related to fertility performance and health traits. Technology, such as Herdvision, aims to use a 2D and 3D camera system to monitor BCS, resulting in greater financial returns and due to improvement in cow heath and fertility, less premature culling, and savings on feeding costs.
Lameness Technology
Lameness is considered to be one of the top cattle health and welfare challenges – although there is notable variation between farms, ranging from 0% to 80%, the average prevalence is estimated to be around 31.6%. Interestingly, a study in 2013 noted that almost 70% of the dairy farmers expressed an intention to take action for improving dairy cow foot health.
Possible barriers to farmers investing in intervention strategies for lameness are labour efficiency – a problem that has only got worse – and the possibility of a laggard effect of achieving an improved dairy cow foot health after taking action. Cattle have a stoical nature and naturally mask the signs of pain. This introduces further bias and subjectivity, and relying on human observation to identify lameness and picking up cows in more advanced stages of pain is insufficient.
Thus, encouraging a technology that can pick up earlier lameness, save on labour, and with more objectivity, can be beneficial to both the animal health and welfare, and the farm’s profitability.
Disease Recognition
As with lameness assessments, monitoring of pain in the UK pig industry relies on human observation, either in person or via video footage, to detect disease. Once again, this introduces challenges, being subjective, time consuming, and impractical for a £1.5 billion industry.
An interdisciplinary team at the University of Newcastle have used artificial intelligence to develop automated systems to analyse and monitor pig behaviour and health. The algorithm was tested in a controlled environment where infection and disease was present, assessing footage of pigs captured by cameras, and pinpointing and quantifying changes in behaviours to identify links to disease.
Other computer vision and AI-based approaches have allowed the automatic scoring of pigs in relation to posture, aggressive episodes, tail-biting episodes, fouling, diarrhoea, stress prediction in piglets, weight estimation, and body size – all providing animal farmers increased insight into the health of their population.
Grazing, land and pasture management
In a bid to make farming as efficient, productive and sustainable as possible, pasture and land management can be supported and enhanced by farms using technologies like Internet of Things (IoT), Artificial Intelligence (AI), and robotics. Such ‘smart farming’ has allowed more efficient pasture and grazing management, moving livestock onto new pastures when the grazing quality and quantity depletes below a certain threshold. Accurate measurement of pasture depletion and, therefore, dry matter intake is fundamental in both research and commercial settings for understanding the behaviour and nutrition of grazing animals.
There are numerous methods of using agri-tech to monitor animals, such as the SheepIT project, an initiative where an automated IoT-based system controls grazing sheep. Typically, such solutions are split into two main groups: firstly location monitoring, and secondary behaviour and activity monitoring. Location monitoring allows farmers to keep track of animals and thus infer preferred pasturing areas and grazing times, and even to detect absent animals. Behaviour and activity monitoring focuses on detecting the type and duration of an animal’s activities, such as resting, eating or running, based on accelerometery and audiometry.
Some companies have enlisted the help of Unmanned Aerial Vehicle (UAV) or ‘drones’ to maximise the efficiency of pasture management and to tackle issues such as cloud cover – which can cause disruption to monitoring systems such as satellites. Scientists have found that combining drones with machine learning techniques to monitor pasture may help farmers control production and improve efficiencies in livestock systems.
Biosensors and biochips
In human medicine, advances in molecular medicine and cell biology have driven the interest in electrochemical systems to detect disease biomarkers and therapeutic compounds. Currently, in human literature, microchip technology and implantable biosensors have been noted in glucose monitoring, DNA detection and cell cultures among others.
Microelectronic technology offers powerful circuits and systems to develop innovative and miniaturised biochips for sensing at the molecular level; these have numerous applications in veterinary medicine from hormone detection, pathogenic microorganism detection, infection monitoring and homeostatic mechanism surveillance such as being applied to pathogen detection in cattle mastitis.
Antimicrobial usage
In 2017, farm animals accounted for around 30% of all antibiotics used in the UK, despite agricultural use in the UK being among the lowest in Europe. A report tracking usage on dairy farms across the British herd from 2017 to 2020 found that the use of injectable Highest Priority Critically Important Antibiotics (HPCIAs), those that the World Health Organisation really needs us to protect for human use, had fallen by 96%. Overall, sales of antibiotics for use in livestock have reduced by 55% since 2014 to the lowest ever recorded level. Incredibly, the annual UK-Veterinary Antimicrobial Resistance and Sales Surveillance report in 2023 showed sales of the products were 9% lower in 2022 than the previous year and down 59% overall since 2014 showing an impressive downward trend in the usage.
Technology has played a direct part in antimicrobial stewardship, alongside the proactive collaborative work of the government, farmers and UK veterinary professionals and paraprofessionals. Using technology to identify health outcomes, provides prompt recognition, allowing quicker intervention before further deterioration – leading to happier and healthier herds.
Conclusion
The story of agri-tech development and application in the UK is one of changes to the political, populational and agricultural landscape. While the use of advanced agri-tech is certainly not commonplace in every UK farm, it is certain that over recent years, more and more farms are looking to invest in and work alongside technology to improve their animals’ health, improve efficiency, profitability and proficiency.
When applied well, and based on good quality data and technology, these initiatives can certainly help rather than hinder. But for farmers, consumers and the wider society to benefit from the agri-tech revolution, the government must help create a marketplace where the innovators in this industry can bring their technology to commercial reality, helping us feed our population and ensure all food producing animals have high welfare.
