Eye on AI - October 23rd, 2020
Welcome to Aigora's "Eye on AI" series, where we round up exciting news at the intersection of consumer science and artificial intelligence!
This week’s “Eye on AI” is all about that harvest, and looks specifically at how new AI-enabled methods in crop breeding and cattle management are enabling farmers to produce yields that are better, healthier, and more resistant to climate disruption.
Researchers Use AI to Breed Crops Suitable for the Changing Climate
Let’s begin by looking at the evolution of crop breeding. Until recently, traditional crop breeding took years to perfect. Farmers would monitor harvests by eye, noting which plants seemed most resistant to drought, then bred the most promising crops together. This process was repeated for years until a fully drought-resistant strain was developed.
Now, with the climate changing faster than ever before in recorded history, weather patterns that had kept relatively consistent are evolving too fast for traditional crop breeding to keep up, threatening our sustainable crop yield with the human population continuing to grow. The solution, notes Carolyn Beans in her PNAS article, “Inner Workings: Crop researchers harness artificial intelligence to breed crops for the changing climate,” is AI-powered crop breeding.
“Using computer science techniques, breeders can rapidly assess which plants grow the fastest in a particular climate, which genes help plants thrive there, and which plants, when crossed, produce an optimum combination of genes for a given location, opting for traits that boost yield and stave off the effects of a changing climate,” writes Beans. “Large seed companies in particular have been using components of AI for more than a decade. With computing power rapidly advancing, the techniques are now poised to accelerate breeding on a broader scale.”
Of course, AI crop breeding isn’t possible without reliant data sources, which many breeding operations already have in excess. Beginning in the 2000’s, plant researchers began collecting enormous data sets that could inform genomics (breeding) decisions. But without AI, they could only analyze small amounts of that data –– the technology couldn’t keep up with the large amounts of data collected.
“Suppose, for example, a wheat breeder has 200 genetically distinct lines. The breeder must decide which lines to breed together to optimize yield, disease resistance, protein content, and other traits. The breeder may know which genes confer which traits, but it’s difficult to decipher which lines to cross in what order to achieve the optimum gene combination. The number of possible combinations… ‘is more than the stars in the universe.’”
Using engineering tools powered by AI, researchers were able to analyze immense data sets to make informed breeding decisions. Complex breeding problems with more possibilities ‘than the stars in the universe’ could be solved with AI when researchers defined their primary objective, then used optimization algorithms to predict the quickest path to a solution. The result was a higher crop yield that maintained genomic traits making them resistant to climate change.
Still, some farming operations don’t have sufficient data to implement AI breeding. Others may have unusable data. For that, many farming operations have begun utilizing drones and other methods to collect crop images for AI analysis. This is all revolutionary stuff. But what’s especially exciting to me is what the future might hold for precision farming, where breeders can easily share their data with one another.
“To probe the genetic underpinnings of climate adaptation for crop species worldwide, Daniel Jacobson, the chief researcher for computational systems biology at Oak Ridge National Laboratory in TN, has amassed ‘climatype’ data for every square kilometer of land on Earth,” continues Beans. “Using the Summit supercomputer, they then compared each square kilometer to every other square kilometer to identify similar environments. The result can be viewed as a network of GPS points connected by lines that show the degree of environmental similarity between points.”
Imagine a farmer in Iowa discovering a new crop ideal for his climate, a farmer working in a similar climate on the other side of the world having access to it, then being able to contact that farmer in Iowa for crop sharing. Or a new farming process for that climate. Or data collection method. We still have a ways to go before that can happen, but the foundations for this kind of revolutionary approach are already there.
Florida Researchers Lead AI Revolution in the Cattle Industry
To supplement the previous story, let’s conclude by looking at AI advances happening in the cattle industry. According to Scott Angle, the University of Florida’s VP for Agriculture and Natural Resources and leader of the UF Institute of Food and Agricultural Sciences, the cattle industry is already being revolutionized by AI, with states like Florida leading the charge.
“Producers may already get more data from sensors and other technologies than any human mind can make sense of,” writes Angle, in his article for South Central Florida Life. “AI can link and analyze all sorts of data that currently exists in separate silos. UF/IFAS animal scientists working with computer scientists and engineers could reveal relationships between data points that inform decisions down to the individual animal.”
The University of Florida already announced a $70 million campus-wide AI initiative earlier this year to address the challenge of food insecurity, with many universities implementing new AI farming programs to ensure future farmers have some level of knowledge and skills related to AI. Precision farming is the future. It’s smarter, more efficient, and cost-effective. While the climate remains in flux, it’s encouraging to hear that the future of farming is in good hands with the help of AI.
That's it for now. If you'd like to receive email updates from Aigora, including weekly video recaps of our blog activity, click on the button below to join our email list. Thanks for stopping by!