Producing food sustainably is one of the greatest challenges facing humanity today. Over-production is common, leading to a huge amount of waste, with more than enough food being produced to feed all of the 8 billion people currently alive on the planet. The World Counts estimates that the 800 million people suffering from hunger and undernourishment could be fed by less than a quarter of the food lost or wasted in the US and Europe.
Implementing sustainable farming techniques, supported by technology, can help tackle this. By deploying IoT sensors across a field and connecting to a private network or local mobile network, farms can monitor their crops, testing water and nutrient levels in the soil. This ensures fertilisers and chemicals are only dispersed when necessary to boost yield; reducing environmental impact (when they’re overapplied, they can also become a pollutant), cost and the need for extra farming staff, important against a backdrop of rising expenditure and ongoing labour shortages. IoT networks can also be used to monitor the performance of farm machinery and irrigation systems while drones can be sent out for routine visual checks of fields.
Monitoring and automating critical tasks like soil irrigation levels can safeguard crop yields and maintain agricultural productivity, even during periods of reduced rainfall. It has been estimated that every 1°C increase in temperature in the UK will create a 27 per cent reduction in water availability for farming and domestic use. For crops such as potatoes and salads, farmers need a guarantee of sometimes two years’ worth of water so they can plan cropping and guarantee supply to the retailers. As climates become more unpredictable, technology can play an important role in providing early warning signals and enabling per-plant precision farming.
Read more below on crop production applications.
Real-time monitoring of environments for smart farm management
According to the UN, about one-quarter of arable land is degraded and needs significant restoration before it can again sustain crops at scale. IoT in crop production helps growers improve the fertility of the land, identify weeds for targeted treatment and protect biodiversity, optimising the environment in which crops grow. From collecting nutrient density information to irrigation levels, temperature and humidity, sensors empower farmers to operate more efficiently and effectively. IoT in agriculture is not necessarily a new concept, but with the addition of advanced connectivity solutions like 5G, the potential grows exponentially, with AI and robotics enabling precision farming at a level not previously seen. Through a process of observing, measuring and responding to various inter- and intra-environment inputs, this technology-enabled approach to farm management allows for more tailored interventions. The smallest changes in on-the-ground conditions such as moisture and temperature can have a big impact on crop outputs. Enabling real-time environmental adjustments helps farmers to prevent and reduce mould, weeds and other threats while providing only the fertilisation and irrigation needed; this reduces costs, creates healthier crops and optimises yields.
Against a backdrop of rising costs of key inputs like fertiliser, real-time monitoring - and the precision management it enables - helps growers to flourish in challenging times, boosting productivity and profitability. If 25% of farms adopted precision farming by 2030, yields would increase by up to 300 million tonnes per year, claims Bell Labs Consulting.
Real-time monitoring of crops for per-plant farming
Crops can also be monitored in real-time, allowing for per-plant farming. With advanced connectivity and the technologies it enables, such as automation, robotics and AI, farmers can monitor each plant’s individual growth, identify biohazards, diseases, signs of plant stress and the best time to harvest. Connectivity solutions such as 5G offer both high bandwidth, allowing for huge amounts of data to be transferred; and low latency, meaning data is transferred in near real-time for time-critical and high-precision interventions such as applying insecticide to a particular plant.
Crucially, growers can use these technologies to predict and identify potential risk factors. From IoT sensors to autonomous drones and machine vision, farmers have access to a level of insight around each plant’s colour and texture down to a pixel level that would never be possible with human workers. This facilitates faster, more tailored corrective action, resulting in better outcomes, higher yields and increased profitability.
‘Per plant’ farming allows for bespoke treatment of each plant, often by automated vehicles. If a scanning machine, either robots in the field or drones flying overhead, recognises a disease on leaf ‘B3’ on plant X1094 then another machine can come and apply fungicide on that leaf, and only that leaf. Approximately 20 to 40% of the produce from cultivated crops die each year globally from diseases and pests so the impact of rapid identification and treatment of problems is significant.
Harnessing the power of big data, smart monitoring, AI and automation can enable agronomists to produce better, more resilient crops. It also supports more sustainable farming; providing customised, rather than uniform, solutions will reduce the use of pesticides, water and waste.
Most IoT networks today cannot support high-resolution imagery transfer between devices, let alone autonomous imagery analysis, nor can they support high enough device numbers and density to monitor large fields accurately. Narrowband Internet of Things (NB-IoT) and 5G promise to solve these bandwidth and connection-density issues.
The 5G RuralDorset project worked with several partners to demonstrate how 5G could enable per-plant farming, with autonomous robots collecting data on individual plants and taking automatic action to improve crop health and yield.
“Intelligent teams of robots which can spot weeds and destroy them naturally have the potential to increase yields by 200% and reduce the need for harmful herbicides and chemicals by up to 95%,” Dave Happy, 5G RuralDorset spectrum and security lead.
EarthSense has produced a ground robot, the TerraSentia, which uses a mix of sensors—including visual cameras, light detecting and ranging (LIDAR) tools and GPS devices—to collect data on the health, physiology and stress responses of a variety of crops. Collecting under-canopy data and insights into maximum daily shrinkage, daily gain, and water deficit, it can scan 10 plants a second. Its cloud-based platform also enables crop scientists to teach the robot to automatically measure a range of key traits like height, condition and leaf-area index.
Insects and rodents can cause untold damage to produce. Insects, in particular, are often hard to detect with the human eye until they’ve created significant damage. Blanket application pesticides and insecticides can play a major role in preventing infestations but pose a variety of unintended consequences including intoxicating plants with harmful chemicals. Additionally, continuous exposure allows insects and bugs to develop resistance, forcing growers to rely on heavier pesticides. Alternative approaches are required to protect the environment, reduce grower costs and align with increasing consumer demand for more sustainable growing practices.
Low-cost image-capturing sensors are an option but can only identify insects that are visible to the naked eye. The Bayer Innovation Lab has developed the MagicTrap -- a smart insect trap equipped with a camera and minicomputer that photographs the inside of the tray at regular intervals and automatically evaluates its contents. The results are visible to farmers via the MagicScout app, saving countless hours of unnecessary trips and inspections.
More sophisticated methods can, however, offer earlier identification. Fluorescence image sensing captures changes in a leaf’s chlorophyll while acoustic or even gas sensors can identify specific chemical compounds which plants produce when stressed. This allows growers to apply insecticides only where and when needed.
Taranis captures data from drones, planes, and satellites covering millions of acres at leaf-level resolution. This allows early identification of potential nutrient deficiency, insect damage and disease, so appropriate - often automated - actions can then be taken.
“With Taranis, we can see insect damage which we’re not going to see otherwise because they are underneath the leaf. If you can find that thing tomorrow morning versus waiting until you see a widespread indication that you have a problem in the field, you can save that producer thousands of dollars”.
Tim Spector, Pride Ag Resources
FOTENIX uses a patented spectral camera and light setup to provide early warning of fungal disease in oil seed rape (OSR) and wheat crops. It is developing a monitor that can be mounted on a tractor or robot, such as those from Small Robot Company or Saga Robotics, enabling early detection and intervention before significant losses.
The system has been shown in trials to be capable of detecting light leaf spots and phoma in OSR and septoria in wheat within five or six days of infection, compared to on average four or five months by traditional methods. Through continuous monitoring, it can also provide evidence of disease control or re-emergence post-application.
But it’s not just during the growth phase where crops are at risk. ContraMoth is a real-time sensor that detects various insects at all stages of their development. The technology senses the pheromones of the adult insect and the semiochemicals of the larvae, detecting at a level not previously achieved.
Smart monitoring could also help farmers optimise the harvesting window. Monitoring crops for quality characteristics—say, sugar content and crop colour—could help farmers maximise the revenue from their crops. Significantly this might mean harvesting different fields at different times to allow for the greatest possible yield across the farm.
Automation for improved efficiencies
The agriculture industry has struggled to recruit the right labour for several years, and the labour shortage, exacerbated by Brexit, has resulted in a 22% rise in wages since 2019. Meanwhile, the average age of a UK farmer is 59 years old; a generation of farmers with a lifetime of knowledge are slowly exiting the workforce against a backdrop of rising costs.
Deploying sensors reduces the need for farm workers to go out into fields to manually collect important data, meaning limited labour can be focused on interpreting data in conjunction with AI, rather than collecting it. Autonomous farming machinery - including drones and autonomous robots - can offer an immediate solution to the problem. The technology performs precise, targeted and individualised interventions based on connected-sensor GPS and imagery analysis, freeing up workers and driving efficiencies.
Increasing the autonomy of machinery through better connectivity could create $50 billion to $60 billion of additional value by 2030, according to McKinsey.
Farmers have historically spent much of their time driving tractors to complete a variety of large-scale agricultural tasks such as ploughing and fertilising. Automation and robotics could help reduce the requirement for what is often a low-skilled labour in this area, while also creating skilled technology jobs which could encourage younger talent into the sector. What’s more, with robots conducting time-critical work, operations can continue 24/7, regardless of the weather conditions.
Unveiled in January 2022, John Deere’s fully autonomous tractor is equipped with six pairs of stereo cameras using AI, enabling 360-degree obstacle detection, geo-awareness and the calculation of distance. The farmer simply has to set up the tractor in a field for autonomous operations and then can operate it via a mobile app while focusing on other tasks. The app provides access to live video, images, data and metrics while allowing the farmer to adjust speed and depth.
Technology-led companies such as Small Robot Company, Muddy Machines and Antobot are also developing commercial services to assist farmers. The Small Robot Company - which successfully demonstrated its capabilities in the 5G RuralDorset project - is rolling out its Per Plant Farming service to 50 farms following findings that it can reduce herbicide applications by 77% and fertiliser by 15%.
Their robot - Tom - scans the crop to a level of detail that identifies individual plants, gathering data on plant and weed distribution to determine the optimum treatment path. Tom can successfully identify all the wheat plants, determining precise plant counts, as well as broadleaf weeds. With a survey speed of 2.2ha/hr, Tom gathers 15,000 images from its cameras, or 40Gb per plant intelligence, for every hectare.
The current offering includes winter wheat crop count and Per Plant visualisation, weed detection, geolocation and per plant imagery, glyphosate, herbicide and fertiliser treatments. Future services currently in development or trials include robotic non-chemical weeding; disease identification and fungicide treatment sprayer export; soil sampling and insights; and grass weed classification, including blackgrass.
Agrointelli is a Danish company that develops autonomous robots for farms. Among other things, they are currently being used by growers to fight volunteer potatoes that spoil sugar beet crops. Potato leftovers grow more quickly and block the sunlight from reaching the sugar beets, preventing them from absorbing sufficient nutrients and growing normally.
The 5G-connected robot is equipped with cameras and precision sprayers. It takes photos of plants and sends them to a cloud-based server. The machine learning algorithm compares these photos with over 6,000 images of weeds and potato plants. After classifying each image, the server sends them back to the robot. If the plant is a potato, the robot sprays it with glyphosate. This full cycle takes approximately 250 milliseconds. Manually spraying volunteer potato tubers takes, on average, 20 hours per hectare and costs around €400. It takes a robot around three hours to process one hectare, with up to 95% of volunteer weeds identified.
Ecorobotix and Naïo also offer autonomous weeding robots that use cameras, AI and machine learning to identify and treat weeds in the field. Companies like Eco Robotics offer similar products, as well as robots that can plant seeds. These agricultural robots work delicately, saving time, reducing laborious work and reducing harm to plants and the environment. More precise GPS controls, paired with computer vision and sensors and advanced connectivity solutions such as 5G, can further advance the deployment of smart and autonomous farm machinery. Soon farmers will be able to operate a variety of equipment on their field simultaneously without human intervention, freeing up time and resources.
Autonomous machines are also more efficient and precise at working a field than human-operated ones, which could generate fuel savings and higher yields.
Drones can also play a key role in automating key processes in the growing process, whether using machine vision and AI to check individual plants or monitoring indoor and outdoor produce to identify the optimal time to harvest. There are several solutions, for instance, the Sense Fly agriculture drone eBee SQ, that use multispectral image analyses to estimate the health of crops. The 5G RuralDorset project demonstrated how with 5G high-resolution field images could be transmitted to farmers in near real-time, meaning they can act on that data most effectively as quickly as possible. This is in contrast to drones being flown over say 4G networks, where data is often downloaded by the farmer and reviewed at the end of the day.
Drones can also play an important role in helping to protect produce in the face of pest infestation. DJI Agriculture was brought to protect farms in China’s Yunnan Province when news arrived of an incoming swarm of yellow-spined bamboo locusts that had already decimated 6,667 hectares of fields. Drones were used for aerial application of anti-locust pesticides and successfully covered 2,000 hectares of land, protecting produce far quicker than traditional spraying methods.
Perhaps the most impressive demonstration of the power of automation is the Hands-Free Hectare initiative, delivered by Harper Adams University. An experimental farm that was formed in Edgmond in 2016, it was one hectare that was managed using a tractor and 25-year-old combine harvester that were converted into autonomous vehicles equipped with cameras, lasers and GPS systems. Strict rules meant no one could set foot on the land, so while the two vehicles prepared the ground, sowed the seeds and maintained the crops, drones were used to capture soil and crop samples and monitor for weeds and disease.
In 2019 the farm expanded to 35 hectares and three self-driving tractors. Except, instead of maintaining a “perfect hectare,” the project looked to challenge the AI-driven machines with more “real-world conditions” that included obstacles and irregular pathways. The original one-hectare harvested two seasons of grain without any manual labour, marking it as the first time something like that happened anywhere in the world.
AI for rapid and precise decision-making
With advanced connectivity, the volume of data that can be collected and transferred to growers in near real-time is vast. However, the data is only valuable if it can be analysed and turned into meaningful insights.
This is where AI comes in. The technology can help farmers both identify risks - such as crop disease or damage - and the optimal time to conduct tasks from watering to weeding and even harvesting. Drones using high-quality and AI-powered cameras can tell apart healthy plants from spoilt crops and weeds. AI analysed sensor data can foresee weather patterns, crop yield, soil nutrients and other factors that directly impact operational efficiency.
Equipping growers with this information ensures quicker action with greater accuracy. Ultimately, this will save time, and cost, optimise crop management and increase yields.
AI-enhanced machinery can be used to help both better monitor and manage environmental risks and diseases, as well as crops themselves. For farmers who want to not only identify risks as soon as they emerge but potentially even move to a predictive model, AI is essential. AI technology can foresee weather patterns, crop yield, soil nutrients and other factors that directly impact farmers’ operational efficiency and cost. When combined with advanced connectivity solutions such as 5G, data can be collated, analysed, trends identified and acted upon in near-real time, saving time and cost.
Generative AI can also be used to automate decision-making, for instance, making strategic decisions about what inputs to apply. The autonomous weeding robots provided by companies such as Ecorobotix and Naïo use cameras combined with AI and machine learning to identify and treat weeds in the field.
Blue River Technology, acquired by John Deere in 2017, has created See and Spray, a device that uses cameras, machine learning and AI to detect weeds in fields. The machine can spray pesticides, fertiliser and fungicides and can help farmers reduce the number of weeds in their crops by as much as 90 per cent in a few years.
On large US corn farms, these solutions have been shown to reduce herbicide costs by 80%, creating a value of $30 per acre and a payback period of two years. Similarly, fertiliser application robots enabled with sensors can control the amount of fertiliser that is directly applied to individual seeds during the planting process. This can save more than 93 million gallons of starter fertiliser annually across US corn farms alone, according to the World Economic Forum.
Similarly, Agrointelli, a Danish company, has developed autonomous robots for farms that can be deployed to tackle volunteer weeds in fields. The 5G-connected robot is equipped with cameras and precision sprayers. It takes photos of plants and sends them to a cloud-based server. The ML algorithm compares these photos with over 6,000 images of weeds and crop plants. After classifying each image, the server sends them back to the robot. If the plant is a crop, the robot sprays it with glyphosate. The full cycle takes approximately 250 milliseconds, almost five times faster than human workers, with 95% of weeds identified. Agrointelli’s smart farming solution, powered by AI, helps farmers automate the process and reduce costs.
ARWAC has been spun out of the Innovate UK-funded project ‘Autonomous Robotic Weeder (in) Arable Crops (ARWAC)’. The consortium combines robotics expertise from the University of Lincoln with industry expertise to provide a mechanised weeding solution for blackgrass control. The objective is to optimise crop production and soil quality through the reduced use of herbicides. Crop losses resulting from competition with blackgrass are expected to be more than £300m, equating to 200k tonnes of wheat lost each year.
The weeding machine uses refined sensors and AI to distinguish between the cereal crop and blackgrass, a challenging task as both have a similar grass-like appearance.
The Hands-Free Hectare, managed by Harper Adams University, is an experimental farm run without any human intervention. In 2019 the farm expanded beyond its initial one hectare to 35 hectares (85 acres) and pivoted from exploring the possibility of technology in perfect conditions to challenging AI-driven machines with more “real-world conditions” that included obstacles and irregular pathways. AI learns through exposure to data so testing how it responds to new and imperfect scenarios is critical to ensure it is suitable for wide-scale deployment across the sector.
AI plays a critical role in supporting automation in crop production. However, it can also play an important part in long-term farm management. Taranis uses AI to provide a season-wide analysis taking into account image-based information—such as sharpness, colour clarity, and other parameters—and field-based information such as field coverage and imagery distribution. With more than 200 million data points Taranis AI models have been thoroughly trained to accurately identify and annotate emerging crops and their potential threats, including signs of diseases, nutrient deficiency, insects, and defoliation. This enables farmers to take both immediate action and longer-term strategic decisions about what crops to grow where and to assess the impact of ongoing climate change.
“With the information we’re getting through from Taranis, we can validate some of the things that we’re doing with fertility, crop protection, plant populations, and equipment performance. We can utilise this information to help validate what we’ve done, what we’re currently doing, and help us make better decisions in the future.”
Glen Franzluebber, Central Valley Ag
It’s no surprise then that the use of AI in agriculture is set to rise. A report by Million Insights estimates that the global artificial intelligence in the agriculture market will reach $2.9 billion by 2025, with a projected compound annual growth rate of 25.4%.
Better protect the natural environment
The agricultural sector is intrinsically linked to the natural environment, yet agricultural practices can have negative impacts. When agricultural fields replace natural vegetation, topsoil is exposed and can dry out. The diversity and quantity of microorganisms that help to keep the soil fertile can decrease, and nutrients may wash out, ultimately reducing potential crop yields.
Agricultural runoff is water from farm fields that doesn’t sink into the soil for proper absorption. Instead, it moves over the ground, picking up natural and artificial pollutants along the way. Eventually, those contaminants get deposited into coastal waterways, lakes, rivers and even underground sources of drinking water.
Technologies, powered by advanced connectivity, are here to help. IoT, robotics and AI can enable real-time monitoring, allowing for precision farming. The chances of overwatering are reduced, fertiliser, herbicide and insecticide are used more sparingly and analysis of data can detect and predict trends and patterns in soil erosion.
More sustainable operations
The world will need to produce around 70% more food by 2050 to feed an increased world population of 9.7 billion, according to estimates by the UN. Still, 14% of food harvested worldwide is currently lost between harvesting and retail, with inadequate harvesting time, climate conditions and harvesting methods all contributing to on-farm losses. While crops themselves are extremely vulnerable to greenhouse gas emissions which raise global temperatures, increase pest and weed infestation, and alter precipitation patterns. New approaches are desperately needed: alongside waste, the chemicals used in agriculture are directly responsible for up to 8.5% of all greenhouse gas emissions, and by 2030 the water supply will fall 40% short of global water needs.
Sensors, AI and automated machinery enable precision farming, providing customised rather than uniform interventions and managing everything from watering to weeding and even harvesting more efficiently and sustainably.
Sustainability has never been more critical, and smart farming may play a key role in food crop production. With conventional farming methods, we risk depleting natural resources while we try to meet the growing need for food, leading to less food of lesser quality, increasing prices and health problems due to lack of nutrients. IoT and automation can enable precision farming, allowing for more efficient use of water and dramatically reducing the use of pesticides and fertilisers.
Following the UK’s departure from the EU, Defra set out its agricultural transition plan The Sustainable Farming Incentive supports sustainable approaches to farm husbandry. This includes actions to improve soil health and water quality, enhance hedgerows and promote integrated pest management. Similar agendas and policies are being ruled out across other nations and regions: for instance, the European Green Deal calls for a 50% reduction in pesticide use compared to 2020 levels.
But not only policymakers are pushing for change: consumers are becoming increasingly aware of environmental impacts, choosing to buy products that demonstrate sustainable practices. Smart monitoring through sensors, connected cameras and automated equipment can digitally record rich data (including growing time and knowing what has been applied to produce), enabling growers to produce more resilient crops and provide field-to-fork traceability to meet demands for reduced chemical application, more efficient irrigation and optimised harvest conditions. This also makes it easier to achieve organic certification.
Companies such as Small Robot Company, Muddy Machines and Antobot are developing commercial services and working with farmers in the field. The Small Robot Company - which successfully demonstrated its capabilities in the 5G RuralDorset project - is rolling out its Per Plant Farming service to 50 farms following findings that it can reduce herbicide applications by 77% and fertiliser by 15%.
The Ted robot produced by Naio Technologies provides a precise mechanised weeding alternative to using herbicides. Automation can play a key role in reducing wastage of produce: harvesting robots can work 24/7, ensuring produce is picked at the optimal time and reducing the chances of produce being left unpicked. With current labour shortages, this provides a tangible solution to a very real problem. Alongside AI, the optimal time to harvest and expected yields can be identified, enabling more effective planning and reduced wastage of produce.
ARWAC has been spun out of the Innovate UK-funded project ‘Autonomous Robotic Weeder (in) Arable Crops (ARWAC)’. The consortium combines robotics expertise from the University of Lincoln with industry expertise to provide a mechanised weeding solution for blackgrass control. The objective is to optimise crop production and soil quality through the reduced use of herbicides. Crop losses resulting from competition with blackgrass are expected to be more than £300m, equating to 200k tonnes of wheat lost each year.
The weeding machine uses refined sensors and AI to distinguish between the cereal crop and blackgrass, a challenging task as both have a similar grass-like appearance.
Precision digital mapping of fields will be used to direct a specially engineered vehicle to provide a sustainable alternative to herbicidal use. ARWAC is currently conducting field trials to test the most effective methods of weed destruction.
“The aim is to develop a mechanical solution that is diesel- and chemical-free and is also lightweight to avoid soil compaction. The machine will help to address both the current labour and environmental challenges that agriculture faces and provide a commercial edge for the industry. A low carbon mechanical approach to weed removal will reduce inputs and bring financial and environmental improvements to the UK farming economy.”
Nick Webster, ARWAC Managing Director
The 5G RuralDorset project also deployed over 40 different 5G-enabled sensors across various trial sites that fed real-time farm data such as soil quality and electricity usage to farmers in a user-friendly visualisation software. This information enabled farmers to make management decisions to reduce waste and improve their farm’s environmental credentials.
Solutions like SoilScout enable farmers to save up to 50% of irrigation water, reduce the loss of fertilisers caused by overwatering, and deliver actionable insights regardless of season or weather conditions. Pycno deployed soil moisture sensors on a farm in Spain, where data showed spikes of humidity immediately after irrigation, indicating the soil was receiving too much water. The irrigation frequency was then able to be optimised, and eventually reduced from twice a day to once every few days. In a few weeks, soil moisture went down to the right level for the crops, and eventually, the farmer used 70% less water on average.
It’s not just water usage that can be reduced through precision farming. A farmer of a large-scale holding in Costa Rica, where the government regulates how many times in a season can spray herbicides, used sensors to measure both crop growth and environmental conditions. This enabled them to identify optimal times to spray on a field-by-field basis, resulting in a 10-15% reduction in spray while maintaining crop yields. Similar solutions are offered by companies such as Cromai, a Brazilian start-up that applies AI to classify weeds, enabling sugarcane plantations to spray precise spots with specific herbicides rather than adopt a ‘spray-and-pray’ approach. Cromai reports their computer-vision capability delivers a 65% reduction in chemical use. Reducing costs, increasing profits and minimising environmental impact.
Real-time monitoring of weather conditions
Agriculture is one of the most climate-sensitive of all economies. Crop production has always been at the mercy of the weather, too much rain and plants become stressed and die, insufficient rainfall and late frost can negatively impact yields. And now the impact of climate change is undeniable, delivering the UK hotter summers, wetter winters, increased likelihood of flooding, and more extreme and unpredictable weather, increasing the risk of large-scale crop failure.
While in the short- to medium-term, the growth of certain crops, such as maize, may benefit from longer growing seasons and higher temperatures, it is expected that in the longer term, changing patterns of rainfall, increased evaporation and reduced water availability will all threaten crop production. All of which has big implications for farmers and the UK’s food security. Small farms are identified as being most vulnerable to changing climate patterns, and around 50% of agricultural land in the UK belongs to smallholdings.
Connected weather and environmental sensors and AI can help detect, analyse and even predict weather events at a hyper-local level. Farmers can track temperatures, wind speed and direction, cumulative rainfall, ambient humidity, dew point, soil moisture, humectation and humidification of crops field by field, enabling them to respond faster to changing conditions and take preventative actions sooner to minimise the chances of crop damage. As well as identifying optimal windows for both seeding and harvesting.
Predictive maintenance of machinery
With profit margins being squeezed, now more than ever farmers need to increase or at least maintain their outputs. One way to support this is by reducing downtime, especially for critical machinery such as weeding or harvesting robots. As crop production embraces the move to automation, the need to improve performance, minimise downtime and extend the lifetime of machinery will become even more vital.
Computer vision and sensors attached to equipment can feed AI models to allow for predictive maintenance, and the identification of early indicators of wear, tear or malfunction. Advanced connectivity, such as 5G, facilitates the capture and processing of more data about how equipment is operating, in real-time. These insights into an asset’s typical efficiency combined with analysis of vibrations, temperature and oil usage for instance, allow a shift to a predictive maintenance model, which impressively, results in detections up to 90 days in advance. This allows for scheduling and controlling of maintenance and repairs, minimising downtime, extending the lifespan of machinery and avoiding wastage from time-based maintenance approaches.
Improve worker safety and satisfaction
According to Safety Nation, agriculture has the worst rate of worker fatal injury (per 100,000) of all the main industry sectors, with the annual average rate over the last five years around 20 times as high as the all-industry rate. Working with hazardous machinery poses significant risks and in emergency scenarios, being able to call for help, whether that’s from other workers or the blue light services is vital and basic, reliable connectivity is essential.
More advanced connectivity can also support both worker safety and satisfaction. Automation of manual, laborious tasks can free workers up to engage in more fulfilling work and potentially remove them from hazardous scenarios i.e. robotic harvesting.
Security of farming equipment
Farm theft is on the rise: in 2023, NFU Mutual, the UK’s leading rural insurer, released a Rural Crime Report estimating rural crime cost the UK £49.5 million in 2022. Quad and ATV theft are increasingly common against a backdrop of increasing costs and a low supply of farm machinery globally. Rural theft has become more organised and steadily increased since the pandemic, shooting up by 22% in 2022. As a result, the UK cost of agricultural vehicle theft reported to NFU Mutual soared by 29% to £11.7m in 2022.
Connected technology solutions are here to help. Connected CCTV and drones can provide real-time feeds of farmland, with 5G enabling ultra-high-definition quality. Expensive farm machinery can be fitted with geo-fencing, which triggers an alarm if it goes beyond farm boundaries.
Optimising post-harvest management to reduce waste
While enough food is produced to feed the population of the entire world, 14% of all food produced never makes it to the consumer, according to the UN Food and Agriculture Organization. This loss, which occurs throughout the production and food supply chain, from harvest up to the retail level, will need to be curbed if the agriculture sector is to successfully feed growing populations while also reducing emissions.
Key causes of on-farm losses include inadequate harvesting time, climatic conditions, harvesting practices, post-harvest infestation from pests and challenges in marketing produce.
Crop waste is one of the factors that contribute to the accumulation of 1 billion tons of annual agricultural waste. According to research by the US National Institutes of Health, 60% of cereal grains are lost during the storage stage due to spoilage. Connected technologies can help.