The food and agriculture chain is one of the most promising industries where the Internet of Things (IoT) can bring about transformational changes. And this transformation includes building smart farm machines to manage crops at the plant level.
To that end, John Deere Labs, which opened its doors earlier this year, made its first major deal on September 6, spending $305 million to acquire Blue River Technology, a startup with computer vision and machine learning technology that can identify weeds–making it possible to spray herbicides only where they’re needed.
Currently, on a global basis, $25 billion is spent each year on about 3.0 billion pounds of herbicides. This has resulted in over 250 species of weeds now considered resistant to herbicides. Over-reliance on a handful of broadcast-spray chemicals fuels the evolution of herbicide tolerance. Fighting these weeds hurts farmers’ crops and their profitability.
The new technology will reduce the need for herbicides by almost 95 percent because computer vision and artificial intelligence will allow the machines to identify, and make management decisions about every single plant in the field, only applying an herbicide to those plants that need treating.
“We welcome the opportunity to work with a Blue River Technology team that is highly skilled and intensely dedicated to rapidly advancing the implementation of machine learning in agriculture,” said John May, President, Agricultural Solutions, and Chief Information Officer at Deere in a press release. “As a leader in precision agriculture, John Deere recognizes the importance of technology to our customers. Machine learning is an important capability for Deere’s future.”
Jorge Heraud, co-founder, and CEO of Blue River Technology said Blue River has basically moved farm management decisions from the field level to the plant level. “We are using computer vision, robotics, and machine learning to help smart machines detect, identify, and make management decisions about every single plant in the field.”
In 2017, Blue River Technology has been listed among Inc. Magazine’s 25 Most Disruptive Companies, Fast Company’s Most Innovative Companies, CB Insights 100 Most Promising Artificial Intelligence Companies in the World, and the Top 50 Agricultural Innovations by the American Society of Agricultural and Biological Engineers.
In 1999, John Deere acquired NavCom Technology, establishing Deere as a leader in the use of GPS technology for agriculture and accelerated machine connectivity and optimization. NavCom is a leading provider of advanced GNSS products for OEMs, VARs and system integrators needing high-performance RTK systems, global five-centimeter level GPS satellite corrections, geodetic quality GNSS receivers, and wireless communication products.
Benefits of the new “See and Spray” technology
The new technology is going to be marketed to cotton farmers first. They are struggling with weeds that have become resistant to the herbicides currently in use. “There are all kinds of weeds developing that you can’t kill with Roundup anymore,” says Willy Pell, director of new technology at Blue River Technology.
Before, farmers would try to use Roundup along with “Roundup-ready” cotton designed to tolerate the chemicals. With the new technology, machines using computer vision tech to identify and spray only weeds will allow a farmer to switch to other herbicides, including organic ones, and target only the weeds.
By using this precision targeting of weeds, only, not only will farmers be using smaller amounts of herbicides but will also see an increase in crop yields. Soybean farmers will be targeted next, says John Deere.
“You can imagine that growers see dollars and cents when they see a 95 percent reduction in herbicide spend–that clearly gets them interested,” Pell says. “But with everything we’re seeing in the last year with herbicide resistance as well as drift, this is becoming a much more important sustainability play as well.”
Agriculture’s future with machine learning technology
Just about every step in agriculture will be made better using computer vision and machine learning, from tilling soil, planting seeds in the optimal locations, spraying fertilizer or nutrients, water usage for irrigation, and harvesting.
All these technologies are needed to prepare the world for population growth which is expected to add 2.4 billion people over the next three decades. Without changes in the agricultural sector, we will not be able to feed everyone. “What that [population growth] translates to in terms of supply is that the global food supply must nearly double,” says Ganesh Jayaram, vice president of information technology for Deere & Co. Agricultural productivity.
Jayaram explains that we don’t have a lot of agricultural lands left to bring under production, but will still have to do more with less. “Seventy percent of it is going to come from technology,” says Alex Purdy, director of John Deere Labs, “and we need to do it in the most sustainable way possible.”