Microsoft opens its AI tools for sustainable farming
On his eastern Washington farm, alongside his long-grown rich harvests of wheat, barley and lentils, fifth-generation farmer Andrew Nelson is adding a new bumper crop to that bounty: Data.
He gathers this data from sensors in the soil, drones in the sky and satellites in space, constantly feeding him information about his farm at distinct points, every day, all year long — temperature variations, soil moisture and nutrient levels, plant health and more. Nelson in turn feeds that data into Project FarmVibes, a new suite of farm-focused technologies from Microsoft Research.
Microsoft has now open sourced these tools so researchers and data scientists — and the rare farmer like Nelson, who is also a software engineer — can build upon them to turn agricultural data into action that can help boost yields and cut costs.
The first open-source release is FarmVibes.AI. It is a sample set of algorithms which run on Microsoft Azure, aimed at inspiring the research and data science community to advance data-driven agriculture.
“Project FarmVibes is allowing us to build the farm of the future,” said Nelson, who has partnered with Microsoft Research to turn his 7,500 acres into a proving ground for Project FarmVibes. “We’re showcasing the impact technology and AI can have in agriculture. For me, Project FarmVibes is saving a lot in time, it’s saving a lot in costs and it’s helping us control any issues we have on the farm.”
Nelson is using this AI-powered toolkit to help guide decisions at every phase of farming, from before seeds go into the ground until well after harvest. He can now predict the ideal amounts of fertilizer and herbicide he should use and where to apply them; forecast temperatures and wind speeds across his fields, determine the ideal depth to plant seeds based on soil moisture and tell him how different crops and practices can keep carbon sequestered in his soil.
By open sourcing its latest research tools, Microsoft wants to help the farming industry tackle the world’s urgent food problem.
“By 2050, we’ll need to roughly double global food production to feed the planet, but as climate change accelerates, water levels drop and arable lands vanish, doing that sustainably will be a huge challenge,” said Ranveer Chandra, managing director of Research for Industry.
“We believe one of the most promising approaches to address this problem is data-driven agriculture and at Microsoft, we are working to empower growers with data and AI to augment their knowledge about farming and help them grow nutritious food in a sustainable way.”
For Andrew, the technology is making a big impact both in his fields and in his bank account. For example, the first year he used data to guide his spraying, the amount he saved was exactly the amount he earned. Earlier this spring, he applied the approach to one-third of his fields and saved nearly 35% on one of his most-used chemicals. After the harvest, he estimates saving an additional 40%.
The AI algorithms being applied, will not only help farmers adapt to a changing climate but they could also help tackle it because by reducing how much water and chemicals farmers use, technology can boost productivity in a sustainable way.
“Agriculture is a cause of climate change, it is most impacted by climate change, but with help from technology it can also be a solution to climate change,” Chandra said.
And although most farmers around the world are not very comfortable with technology, Microsoft wants to inspire academic and industry partners to translate this research into tools that can be used by all farmers, including the smallholder farms in the developing world.
“This is why we are open sourcing – to make this technology available to the community so that they can bring the best in soil science to the best in computer science to unlock the opportunity to help enable sustainable agriculture,” said Microsoft.
Andrew Nelson concluded “I think this is just like how computing has progressed – everything keeps building on everything that came before. My grandfather farmed 750 acres and today, with more powerful equipment, I can farm 7,500 acres. With Project FarmVibes, technology is helping me get back to farming on that smaller scale – acre by acre, instead of field by field – because I have such a fine-grained understanding of the land.”