5G in Livestock Management

The 5GRIT project trialled UAV remote surveying of grazing livestock, primarily sheep, on a  600Ha farm outside of Slaggyford, Northumberland, a remote upland environment. Over a 5G network, the in-field transmission of survey data to a remote cloud server was completed around three to four times faster when compared with existing 4G data speeds. 

The project also developed an AI livestock detection algorithm to survey and assess livestock and achieved 86% accuracy. Indications suggest that this accuracy value could be further improved through additional data-set training and optimisation for wider detection targets, allowing for further livestock analysis. 5GRIT, which worked closely with the farming community during the project, estimated time savings from remote UAV farm surveying could reduce labour requirements by £600 per month. Additional cost efficiencies could be enabled through regular remote aerial surveillance, facilitating early identification of livestock health and enabling farm security benefits.

The TailTech research project focused on the problem of tail-biting among pigs, which can start without warning or an obvious traceable cause. Though generally beginning as a low-grade problem for farmers, an outbreak can spread rapidly, resulting in pain, sickness and infection for the pigs. This, in turn, results in abattoir condemnation of meat and economic losses to the farmer, alongside additional costs from veterinary treatments. 

Creating an early-detection system, based on research that suggests tail biting might be detected by the posture of a pig’s tail, TailTech deployed 3D cameras and mission vision software to enable automated detection of changes in tail posture. This not only improves animal welfare, reducing the need for practices like tail docking of piglets but minimises the likelihood of economic losses. 

Harper Adams University is also conducting research into the application of machine learning. To predict pen fouling, diarrhoea and tail biting in commercially farmed indoor pigs,  its RoboChick project has developed a small autonomous vehicle, which sits at approximately bird head height and is capable of collecting high-resolution data - such as temperature, humidity, carbon dioxide level, air flow velocity and light spectrum - within broiler chicken buildings. The project is only in its research stage but provides positive indications of how connectivity and new technologies can improve the tracking and monitoring of animals at the herd level.

The South West Dairy Development Centre, run by Agri-EPI, is a high-performing dairy innovation unit featuring the latest robotic and sensor technology. Robotic milking systems allow the cows to choose when they are milked, while connected collars prevent over-milking and grant them free access around the farm. The robots also provide high levels of data to be able to monitor each cow’s output and identify potential problems (for example, if output suddenly drops). This, alongside the data from their connected collars - which offer insights into eating, sleeping and movement patterns - all provide a far more granular insight into the cow’s wellbeing than can be achieved through manual inspection.

An automated feed system reduces human-cow interaction, a potential cause of stress. Their environment is also monitored and continually optimised via automated side curtains which control airflow and adjust according to wind speed, rainfall and internal temperature.

The 5G RuralDorset project explored the potential of 5G to transform the welfare of dairy herds. Connected camera installations enabled live images from the milking parlour to be transferred in real-time to Kingston Maurward College: CattleEye analysis software was used to monitor the health of the cattle remotely and make timely intervention decisions across the herd.

The TailTech research project focused on the problem of tail-biting among pigs, outbreaks of which can start without warning or an obvious traceable cause. Though generally beginning as a low-grade problem for farmers, an outbreak can rapidly spread, resulting in pain, sickness and infection for the pigs. This, in turn, results in an abattoir condemnation of meat and economic losses to the farmer, alongside additional costs from veterinary treatments. 

Creating an early-detection system, based on research that suggests tail biting might be detected by the posture of a pig’s tail, TailTech deployed 3D cameras and mission vision software to enable automated detection of changes in tail posture. This not only improves animal welfare,  reducing the need for practices like tail docking of piglets but minimises the likelihood of economic losses. 

Harper Adams University is also conducting research into the application of machine learning. To predict pen fouling, diarrhoea and tail biting in commercially farmed indoor pigs, its RoboChick project has developed a small autonomous vehicle, which sits at approximately bird head height and is capable of collecting high-resolution data - such as temperature, humidity, carbon dioxide level, air flow velocity and light spectrum - within broiler chicken buildings. The project is only in its research stage but provides positive indications of how connectivity and new technologies can improve the tracking and monitoring of animals at the herd level.

Further afield, the Voshazhnikovo Farm in Russia has transformed into a “smart farm” to increase its milk production. Technology partners installed environmental sensors inside the farm to collect data on temperature, pressure, humidity, and lighting conditions. This information is transmitted via LoRaWAN connectivity to the farm’s ERP system, where it is added to the dataset along with external information.

Individualised feeding and care plans can be created for dairy and beef cattle based on connected body sensor data and movement tracking. This is aimed at detecting illnesses early and providing each animal with optimal feed and medicine mix to maximise growth. Chips and body sensors can measure temperature, pulse, and blood pressure, among other indicators, preventing herd infection and improving food quality. Farmers are already using ear-tag technology from providers such as Smartbow (part of Zoetis) to monitor cows’ heat, health, and location and technology from companies such as Allflex to implement comprehensive electronic tracing in case of disease outbreaks. The South West Dairy Development Centre in Somerset is a high-performing dairy innovation unit featuring the latest robotic and sensor technology. Robotic milking systems allow the cows to choose when they are milked, while connected collars prevent over-milking and grant them free access around the farm. The robots also provide high levels of data to be able to monitor the output of individual cows and identify potential problems. Alongside the connected collars, this provides a greater insight into the well-being of the cows than can be achieved through manual inspection.

The Healthy Heifer project - led by Cambridge Animal Technologies, in partnership with the Agri-EPI Centre - uses smart ear tags and a data analysis platform to capture and assess the genetics of animals. This includes nutrition, environment, activity and health to inform decisions that will optimise health. Retaining healthier heifers and reducing the number of new heifers needed will improve a herd’s overall longevity, productivity and profitability, while also supporting a more sustainable way of farming. The ultimate aim of the project is to see 95% of the herd reach first lactation, halve losses and reduce the average first calving to 24 months. It is currently 26 months in most British dairy farms. 

Specific solutions can also support the conception and calving processes, as well as monitoring calves during their critical first days of life. MooCall is an Irish farmer-based agritech start-up that produces IoT sensors for cows. Its MooHEAT solution comprises a collar worn by a stock or a teaser, also known as vasectomised bull and ear tags attached to all cows and heifers. The collar then uses the proximity of the cow or bull, mounting behaviour and activity levels to determine when a cow or heifer is in heat to a high degree of accuracy. It can also identify likely due dates and monitor a cow’s fertility over time. Since using the technology, Ciarán Lenehan, a suckler farmer from Co. Meath has seen conception rates on his farm increase from 75-85% to over 90%.

MooCall also has a calving device, which focuses on combating the high cow mortality rates during calving. When a cow gets a contraction, her tail moves in a specific way and the device attaches to a cow’s tail and tracks those movements to monitor her contractions. The sensor has been shown to reduce the number of fatal births by half, helping farmers to save up to four hours per day per cow during a calving season.

Agri-tech solutions initially focused on older stock but solutions that monitor and protect the wellbeing of calves are now becoming available. The need for such solutions is great, with the importance of early disease detection in the early stages of a cow’s life well established. Calf scours (a clinical sign associated with several diseases, resulting in diarrhoea) cause more financial losses to calf producers than any other health problem in their herds. The prevalence of bovine respiratory disease (BRD) or calf pneumonia during the rearing period sits at a rate of approximately 20%, the most common reason for death and poor performance in calves and young, growing cattle.

To suppress and avoid the spread of diseases, calf farmers are heavily reliant on the use of antibiotics. However, the overuse of antibiotics can quickly lead to resistance and prolonged usage can enhance its persistence. Monitoring health at an individual level will optimise treatment, while early-life management offers significant benefits to both animal welfare and yields. 

The WELL-CALF project - funded by Innovate UK - developed the first cloud-based decision support platform, which serves different levels of decision-making on dairy and beef farms. WELL-CALF’s precision agriculture technology is focused on monitoring calves from seven days to sixteen weeks old, providing support for farm-level decisions (for example, health management and nutrition) as well as policy and practice decisions at the systems level.

Machine vision can also be used to monitor and assess animals individually. As a part of the 5G RuralDorset project, Wessex Internet partnered with CattleEye, using cameras to improve cattle welfare. The images are taken when the cow is being milked to decide if cattle are lame or unhealthy, but it is 5G that helps this data get back to the farmer straight away, ensuring the cattle are treated quickly.

Such technologies can also be used to address particular risk areas for livestock. Lameness is a key issue in dairy herds, for instance, with 25% of dairy cattle in the UK suffering at any one time, impacting milk production. The cows are susceptible to a range of hoof issues which often show a visual change on the underside and back of the hoof. The Hoofcount Automatic Footbath was developed with funding from Defra and Innovate UK to detect these early indicators and enable earlier treatment.

Individual monitoring of animals in real-time offers significant benefits. The SmARtview research project has taken this one step further, combining an AI-based system, which can recognise cows by their skin patterns and an AR headset, displaying health and productivity data. This enhances farmers’ knowledge of their cows' and vets’ expertise to deliver instant, individual data retrieval for faster and more accurate cow-side decision-making.

Duncan Forbes, Agri-EPI Head of Dairy explained:

“The beauty of this project is that it combines farmers’ and vet’s experienced ‘eyes’ with real-time data: technology is being used to enhance, rather than replace, human skills. In addition, SmARtview could provide a solution to one of the key challenges of on-farm technology – while different devices like robotic milkers, sensors and collars can already collect plentiful data, its lack of integration limits insight to drive decision-making.”

Precision livestock management is also possible in poultry farming. Poultry farmer Peter Mason, farm manager of Uphouse Farm Ltd. takes a data driven approach to his farm’s broiler business. This includes live monitoring of key performance metrics such as FCR (food conversion ratio), live weight gain and the daily feed and water intake of each bird.

Attention to detail is crucial in poultry farming, one drinker line or pan line at the wrong height can impact the performance of thousands of bird in a shed. For Mason, with seven and a half flocks each year, across two farms, such issues can have a significant impact on bird importance. Being able to monitor and respond to per-bird data is critical to his long term profitability and success. 

“We are an 840,000-bird site spread across two farms, both running the higher welfare, in-house hatching ‘Nestborn’ system. We have two great teams of stockmen who are all dedicated to achieving the highest welfare and performance from our birds. The technology we have installed in the sheds gives them a great platform on which to achieve this, and allows us to collect daily performance data and analyse it. If there is a drop in performance, we analyse the information to try and understand the cause”.

The South West Dairy Development Centre, run by Agri-EPI, is a high-performing dairy innovation unit featuring the latest robotic and sensor technology. Robotic milking systems allow the cows to choose when they are milked, while connected collars prevent over-milking and grant them free access around the farm. The robots also provide high levels of data to be able to monitor each cow’s output and identify potential problems. This, alongside the data from their connected collars - which offer insights into eating, sleeping and movement patterns - provides a more granular insight into the cow’s wellbeing than can be achieved through manual inspection.

An automated feed system reduces human-cow interaction, a potential cause of stress. Their environment is also monitored and continually optimised via automated side curtains which control airflow and adjust according to wind speed, rainfall and internal temperature.

The 5G RuralDorset project also explored the potential of 5G in dairy farming. Connected camera installations enabled live images from the milking parlour to be transferred in real-time to Kingston Maurward College. CattleEye analysis software was used to monitor the health of the cattle, without the need for stressful human interactions, and make timely intervention decisions across the herd.

The Voshazhnikovo Farm in Russia has transformed into a “smart farm” to increase the milk production of its cows. Environmental sensors monitor temperature, pressure, humidity, and lighting conditions. The information is transmitted via LoRaWAN connectivity to the farm’s ERP system, where it is added to the dataset along with external information. Automatically collecting the data enabled the farm to identify that feed costs had increased and milk yields declined in higher temperatures. Armed with these insights, they were able to automate temperature thresholds and subsequent ventilation: as a result, milk production on the farm increased from 28 to 33 litres per cow.

Similar deployments have been made elsewhere. IMO Automation worked with a livestock farm in the US to optimise its barn ventilation system using automation technology. The farm had been facing several issues due to inadequate ventilation, including higher energy bills and reduced productivity. Sensors were installed to measure the temperature, humidity, and ammonia levels in the barn, connected to a control system that could adjust the ventilation system automatically. 

As a part of the Worcestershire 5G project, manufacturer Mazak successfully deployed automated remote predictive maintenance. Taking advantage of 5G’s ability to process large amounts of data, the factory is now able to provide real-time analysis of machine status and feed this information to a cloud system. The company’s spindles are usually only removed for corrective maintenance after an issue or failure occurs but with the arrival of 5G, early warning signs of damage are available; this reduces repair costs, as well as downtime.

The Port of Felixstowe used 5G IoT devices and predictive data analytics to reduce unscheduled downtime of its 31 quay-side and 82-yard cranes. AI optimises the crane’s predictive maintenance cycle, which improves performance and the productivity of ship-to-shore operations. 

These examples, though from other sectors,  demonstrate the important role connectivity can play in digitising the maintenance process, facilitating early detection of faults and minimising downtime. This can have a significant impact on the bottom line, something that is needed in the farming industry where costs are spiralling.

Producing one kg of edible protein from insects requires much less land and water than conventional livestock feed, reducing greenhouse gas emissions and costs. Mass-rearing costs can potentially be much lower too. Insects fed on agricultural by-products help to reduce waste, lower costs and enable circular economic business models. 

SmartBreed is a Swiss agricultural start-up that produces IoT-connected breeding boxes, supporting farmers to grow grasshoppers that serve as feed for hens. The connected box creates optimal rearing conditions for insects. It uses sensors to automate breeding by monitoring the temperature, humidity, CO2 values, microclimate, and day–night rhythm. Currently reducing the breeding time by three weeks, SmartBreed expects this to fall to two weeks when powered by 5G, which can transfer higher volumes of data in near real-time. Image recognition will be able to measure the size and colour of the insects while AI can recognise the grasshoppers’ moulting phases, adjusting to required parameters.

The Voshazhnikovo Farm in Russia has transformed into a “smart farm” to increase its milk production. The farm has 4,500 dairy cows which each produce an average of 28 litres of milk per day.  Rising temperatures had affected the cows’ appetite, resulting in increased feed and food expenses, and reduced milk production. 

To combat this, technology partners installed environmental sensors inside the farm to collect data on temperature, pressure, humidity, and lighting conditions. This information is transmitted via LoRaWAN connectivity to the farm’s ERP system, where it is added to the dataset along with external information. The owners were able to identify when conditions were becoming unfavourable and take the required steps (for example, increasing ventilation). Over 180 days, the farm saved €340,000 on feed costs for 2,000 dairy cows and milk production increased by 18 percent to 33 litres per cow per day.

Worryingly, the UK is now experiencing wildfires due to increased temperatures, which can have devastating impacts on grazing land and risk to life for livestock.  A fire can spread up to 200 metres every minute: by the time a wildfire has been spotted by a farm worker, the damage can be significant. Ericsson SmartForest is a solution that uses sensors and AI to detect and monitor wildfires, enabling faster response times.  

"We're now treating wildfires as business as usual. And the conditions are going to get more extreme as the next two decades move on," said Surrey fire investigation officer Matt Oakley.

The Voshazhnikovo Farm in Russia has transformed into a “smart farm” to increase its milk production. The farm has 4,500 dairy cows which each produce an average of 28 litres of milk per day. Rising temperatures had affected the cows’ appetite, resulting in increased feed and food expenses, and reduced milk production. 

To combat this, technology partners installed environmental sensors inside the farm to collect data on temperature, pressure, humidity, and lighting conditions. This information is transmitted via LoRaWAN connectivity to the farm’s ERP system, where it is added to the dataset along with external information. The owners were able to identify when conditions were becoming unfavourable and take the required steps (for example, increasing ventilation). Over 180 days, the farm saved €340,000 on feed costs for 2,000 dairy cows and milk production increased by 18 percent to 33 litres per cow per day.

The Ritchie Beef Monitor is an automated weighing crate. Complete with fitted water troughs and 3D cameras, it allows farmers to monitor the live weight and gains of individual cattle through compatible ear tags. The information is then sent to an online platform that is accessible by farmers.

The technology allows farmers to track optimum finishing points for individual animals, which reduces labour needs, minimises stress for livestock and offers clear health and safety benefits.

5G RuralDorset’s connected cow initiative enabled the location of animals to be tracked in real-time, preventing rustling and facilitating the recovery of livestock. On the commercial market, solutions such as Digitanimal offer GPS locator devices for sheep, cows, goats and horses, tracking animal movements and sending notifications to farmers if an animal leaves the farm.

Tim Price, Rural Affairs Specialist at NFU Mutual, said: “By combining modern technology with physical fortifications, farmers are trying to keep one step ahead of the thieves”.