swarms of drones buzz overhead, as robotic vehicles crawl across the landscape. Orbiting satellites capture high-resolution images of the scene far below. No human being can be seen in the pre-dawn glow spreading across the land.
This is not a post-apocalyptic vision of the future à la The Terminator. This is a snapshot of the farm of the future. Each phase of the operation – from seed to harvest – may one day be automated, without the need to get your nails dirty.
In fact, it is science fiction that is already becoming reality. Today, robots equipped with artificial intelligence can remove weeds with supernatural precision, while autonomous tractors move tirelessly across the farmland. Satellites can assess crop health from outer space, providing tons of data to help produce the kind of business intelligence that was previously only accessible to Fortune 500 companies.
“Precision agriculture is on the verge of a new phase of development involving intelligent machines that can operate on their own, which will allow production agriculture to be significantly more efficient. Precision agriculture is becoming robotic agriculture, ”said Professor Simon Blackmore last year during a conference in Asia on the latest developments in robotic agriculture. Blackmore is director of engineering at Harper Adams University and head of the National Center for Precision Agriculture in the UK.
It is Blackmore University that recently showed what might one day be possible. Called Hands Free Hectare and led by researchers from Harper Adams and private industry, the project cultivated one hectare (about 2.5 acres) of spring barley without a person setting foot in the field.
The team redesigned, rewired and robotized farm equipment ranging from a Japanese tractor to a 25-year-old combination. The drones served as scouts to study the operation and collect samples to help the team monitor the progress of the barley. At the end of the season, the robbery farmers harvested around 4.5 tonnes of barley at a price of £ 200,000.
“This project was intended to demonstrate that there is no technological reason why a field cannot be cultivated without humans working the land directly, and we have,” said Martin Abell, mechatronics researcher for Precision Decisions, who was associated with Harper Adams. , in a press release.
Me, Robot Farmer
Harper Adams’ experiment is the latest example of how machines are altering the agricultural industry. Around the same time that the Hands Free Hectare combine harvested barley, Deere & Company announced that it would acquire a new company called Blue River Technology for a reported amount of $ 305 million.
Blue River has developed a “see and spray” system that combines computer vision and artificial intelligence to discriminate between crops and weeds. Hit the former with fertilizer and apply the latter herbicides with such precision that it can remove 90 percent of the chemicals used in conventional agriculture.
It is not just farmland that is helping robots. A Californian company called Abundant Robotics, which grew out of the nonprofit research institute SRI International, is developing robots capable of picking apples with vacuum-like arms that suck fruit directly from trees in orchards.
“Traditional robots were designed to perform very specific tasks over and over again. But robots that will be used in food and agricultural applications will have to be much more flexible than what we have seen in automobile manufacturing plants to deal with the natural variation of food products or the outside environment, “Dan Harburg, an associate at venture capital firm Anterra Capital, which previously worked at a Massachusetts-based company that manufactured a robotic arm capable of gripping fruit, he told AgFunder News.
“This means that ag-focused robotic startups have to design systems from scratch, which can take time and money, and their robots have to be able to complete multiple tasks to avoid staying on the shelf for much of the year.” He noticed.
Eyes on the Sky
It will take more than an army of robotic tractors to successfully cultivate. The farm of the future will have drones, satellites and other airborne instruments to provide data on its crops in the soil.
Companies like Descartes Labs, for example, use machine learning to analyze satellite images to forecast soybean and corn yields. The Los Alamos, New Mexico startup collects five terabytes of data each day from multiple satellite constellations, including NASA and the European Space Agency. Combined with time readings and other real-time inputs, Descartes Labs can predict cornfield yields with 99 percent accuracy. Its artificial intelligence platform can even assess crop health from infrared readings.
The US agency DARPA recently awarded Descartes Labs $ 1.5 million to monitor and analyze wheat yields in the Middle East and Africa. The idea is that accurate forecasting can help identify regions at risk of crop failure, which could lead to famine and political unrest. Another company called TellusLabs of Somerville, Massachusetts also employs machine learning algorithms to predict corn and soybean yields with accuracy similar to that of satellite imagery.
Farmers do not have to reach orbit to obtain information about their farmland. An Oakland startup, Ceres Imaging, produces high-resolution images from multispectral cameras that fly through fields aboard small planes. Snapshots capture the landscape at different wavelengths, identifying insights into issues like water stress, and providing estimates of chlorophyll and nitrogen levels. Geotagged images mean that farmers can easily locate the areas that need to be addressed.
Growing from the inside
Even the best intelligence, whether from drones, satellites, or machine learning algorithms, will be challenged to predict the unpredictable problems posed by climate change. That is one of the reasons why more and more companies are betting on the farm in what is known as controlled environment agriculture. Today, that doesn’t just mean sophisticated greenhouses, but everything from warehouse-sized automated vertical farms to robot-built rooms, located not in the Kansas or Nebraska void but right in the middle of America’s main streets.
Proponents of these new concepts argue that these high-tech indoor farms can produce much higher yields while dramatically reducing water consumption and synthetic inputs like fertilizers and herbicides.
San Francisco’s Iron Ox is developing one-acre urban greenhouses that will be robotically operated and reportedly capable of producing the equivalent of 30 acres of farmland. Powered by artificial intelligence, a team of three robots will execute the entire operation of planting, nurturing and harvesting the crops.
Vertical agriculture company Plenty, also based in San Francisco, uses AI to automate its operations, and obtained a $ 200 million vote of confidence from the SoftBank Vision Fund earlier this year. The company claims that its system uses only 1 percent of the water consumed in conventional agriculture and produces 350 times more products. Plenty is part of a new crop of urban farms, including Bowery Farming and AeroFarms.
“What I can imagine is locating a larger-scale inland farm in the desert for economically disadvantaged food, to spur a broader economic impact that could create jobs and generate income for that area,” said Dr. Gary Stutte, the agriculture expert. space. and controlled environmental agriculture, in an interview with AgFunder News. “The inland agriculture model is adaptable to become an engine for economic growth and food security in rural and urban food deserts.”
Still, the model is not without its own challenges and criticisms. Most of what these farms can produce falls into the “leafy greens” category and often comes at a premium price, which seems to be antithetical to the proposed mission to create oases in the food deserts of cities. While water usage can be kept to a minimum, the electricity required to power the operation, especially LEDs (which played an important role in the inland agriculture revolution), are not cheap.
Still, all of these advances, from farmer robbery to automated greenhouses, may need to be part of a future where nearly 10 billion people will inhabit the planet by 2050. A statistic quoted from the United Nations Agriculture Organization and Food says the world must boost food production by 70 percent to meet the needs of the population. Technology may not save the world, but it will help feed it.