Alphabet’s X lab, the former Google division that unveiled the self-driving car unit Waymo and other ambitious projects, has taken the wraps off its new “moonshot”: a computational agriculture project the company is calling Mineral. According to project leader Elliott Grant, the project focuses on sustainable large-scale food production and farming, with a focus on “developing and evaluating a variety of software and hardware prototypes breakthroughs in artificial intelligence, modelling, sensors, robotics and more.”
A blog post outlining the vision of the project says that Mineral, which now has an official name but was formally announced back in 2019, will try and target technology to solve sustainability problems. These include feeding the growing population of the Earth and more efficiently producing crops by understanding growth cycles and weather patterns. The project also hopes to control land and plant life as the effects of climate change complicate ecosystems.
“To feed the planet’s growing population, global agriculture will need to produce more food in the next 50 years than in the previous 10,000 — at a time when climate change is making our crops less productive,” reads the latest Mineral website.
“Just as the microscope led to a transformation in how diseases are detected and managed, we hope that better tools will enable the agriculture industry to transform how food is grown,” explains Grant. “Over the last few years, my team and I have been developing the tools of what we call computational agriculture, in which farmers, breeders, agronomists, and scientists will lean on new types of software, hardware, and sensors to collect and analyze information about the complexity of the plant world.”
A new four-wheel rover-like prototype is one of the first of these tools, which the Mineral team is calling plant buggy, study crops, soil, and other environmental factors uses a mix of cameras, sensors, and other equipment. In order to create predictive models for how plants will grow using machine learning and other AI training techniques, the team then uses the data collected and combines it with satellite imagery and weather data. The Mineral Team says the prototypes are already being used in Illinois to research soybeans and California strawberries.
“Over the past few years, the plant buggy has trundled through strawberry fields in California and soybean fields in Illinois, gathering high-quality images of each plant and counting and classifying every berry and every bean. To date, the team has analyzed a range of crops like melons, berries, lettuce, oilseeds, oats and barley—from sprout to harvest,” reads Mineral’s website.
Grant says the mineral team will work with plant breeders and growers, farmers, and other agricultural experts to come up with practical solutions with real-world benefits. But there is a high-minded ambition for the project. And the track record of Alphabet is high in the department. Waymo is now a leading self-driving car business that has just opened up its fleet of driverless cars to Phoenix residents.