2 U of S scientists granted access to new Microsoft technology for crop research

Two University of Saskatchewan computer scientists have been selected as grant recipients of Microsoft’s “AI for Earth” program. AP Photo / Ted S. Warren

Two scientists at the University of Saskatchewan (U of S) have been selected to use new Microsoft technology for their research on improving crops.

Tony Kusalik and Ian Stavness are among the first grant recipients of Microsoft’s “AI for Earth” program.

The program, launched in July, is aimed at empowering people to solve global environmental challenges by increasing access to artificial intelligence (AI) tools and educational opportunities.

Kusalik intends to uncover the relationship between plant genes and desirable traits.

“We hope the new Azure AI cloud computing platform will help us to enhance deep learning to recognize complex patterns in plant genes so that we can find desirable ones,” Kusalik said in a press release.

Story continues below advertisement

“Finding the links between plant genes and favourable crop traits will help breeders speed up their breeding programs.”

Stavness will be using Microsoft Azure cloud computing resources to create ways to analyze images and videos of plants to automatically identify traits related to growth, health, resilience and yield.

“Having a computer recognize these traits has potential to increase speed, reliability and precision of trait identification and will provide new opportunities for crop breeders and farmers to directly compare large numbers of individual crops with differences in genetics, growing environment and crop management,” Stavness said in a press release.

Both U of S computer scientists are part of a program at the Plant Phenotyping and Imaging Research Centre (P2IRC) that is working to transform crop breeding and provide solutions to global food security.

So far, over 35 AI for Earth grants, valued at $10,000 each, have been distributed by Microsoft to qualifying researchers and organizations around the world.

Sponsored content