Agtech: Where farming meets robotics, AI and the IoT
The robot farmer is here, says Chris Middleton, but the biggest agtech innovations will come from the IoT, big data, and analytics.
As someone once observed, you can make a small fortune in farming, provided you start with a large one. Agtech investment is certainly booming, according to Crunchbase data, with $320 million raised by startups in 2017 alone.
Farming has always been in the vanguard of automation, and so it is no surprise that this seasonal, cost- and labour-intensive industry is now at the forefront of robotics development, with drones, driverless tractors, and autonomous harvesters all entering the field, in every sense. In 2017, for example, researchers in Shropshire claimed a world first when they used robots to both plough and sow a field of barley, while companies such as FFRobotics and Abundant Robotics are among the many developing smart harvesting machines.
Aerial drones fitted with multispectral cameras are already being used on large farms to spot which areas need more irrigation or fertilisation, and these can be linked with autonomous tractors and other vehicles that concentrate on watering and feeding the crops in those areas.
As with industrial robotics in manufacturing, the emerging generation of robot farmers will be smaller, smarter, and more programmable, and able to carry out complex tasks more efficiently, such as fruit picking, harvesting, hoeing, or site-specific crop and weed management. These disciplines are already becoming automated to a large degree by industrial-style machines.
With modern farming also reliant on seasonal labour, and on pesticides and herbicides that can enter the food chain, the opportunity is there to make farming much smarter. And this is where the Internet of Things and big data analytics also come in.
AI, analytics, and smart supply chains are an increasingly vital part of the farming revolution. For example, US startup Aerofarms (“farming locally, globally”) is among the many organisations using big data to reinvent agriculture from the ground up, via so-called vertical farming. Rivals include the startups Bowery Farming and Plenty.
Vertical farms produce crops indoors in vertical, stacked layers, meaning that they can be integrated with urban or industrial environments, using techniques such as hydroponics to keep the plants watered and fed with nutrients. Another startup, Freight Farms – which produces self-contained farms in shipping containers – offers an alternative version of the model.
By moving crops indoors into sensor-controlled, LED-lit environments – vast libraries of crops – Aerofarms claims that it can achieve between 130 and 390 times the productivity of traditional field farming, using less land, 95 per cent less water, zero soil [see picture].
Founded in New Jersey in the US, Aerofarms uses aeroponics to nurture its crops, via a patented, nutrient-filled mist, and a cloth layer in place of soil – a technology that was the brainchild of Ed Harwood, a professor at Cornell University’s agriculture school.
“Our mission is to build farms in cities all over the world,” says Aerofarm co-founder and CEO David Rosenberg, who explains that his company “grows locally to be where the mouths are”. This reduces the environmental impact of the traditional food supply chain, he claims, an aim shared by all vertical farming companies.
Aerofarms claims that its crops are stronger, greener, and tastier, without the use of genetics or harmful chemicals – all thanks to big data. So how are companies such as Aerofarms using analytics and the IoT? Rosenberg explains that, like human beings, crops are highly susceptible to how well nurtured and supported they are as they grow, and to the stresses and strains of their environment.
Aerofarms deploys thousands of sensors in its vertical farms, which create hundreds of thousands of data points. “We’re trying to understand how we optimise yield via a different light spectrum, different nutrients, and so on,” says Rosenberg.
By gathering data about how and why crops flourish, Aerofarms says it can create the ideal conditions for each crop all the year round, regardless of season, rainfall, or temperature. “For example, our kale is very smooth and less bitter. This comes from the IoT side,” says Rosenberg. “We’re a farming company, but we’re also very much a technology company. The technology enables us to be a better farming company, and being farmers allows us to be a better technology company.”
The other side of the fence
But is it really that simple? Critics of vertical farming suggest that, despite the innovations involved and the determination to minimise food miles and integrate crops with urban environments, the sustainability claims made for the technology are partial, at best.
Vertical farms demand huge amounts of heat, light, and electricity – often from fossil fuel sources – energy that, in traditional farming, is freely available from the sun. Some suggest that integrating traditional farming with the unused roof spaces in cities would be a simpler, more energy-efficient solution.
In the US, another company, BrightFarms, claims that its smart-greenhouse-based solutions offer a better model for reducing food miles, with a reduced carbon footprint, while companies such as Arable and Prospera are producing solar-powered sensors and data analysis tools to help all farmers to gather data about their crops.
Whoever is right, the use of the IoT and big data analytics by Aerofarms and others points towards a more efficient future, whichever farming model proves to be the most sustainable and energy efficient in the long run. With water security, soaring temperatures, and environmental change high on most countries’ agendas, all attempts to make farming smarter in an unpredictable future are welcome.
• David Rosenberg was speaking at Dell Technologies’ IoT Strategy Day in New York, 10 October, 2017, attended by Chris Middleton.
• A version of this article was first published on Hack & Craft News.
© Chris Middleton 2017.