AI tool to identify agricultural pests in development

Iowa State University researchers are developing large, vision-based artificial intelligence tools to identify and then recommend controls for agricultural pests.

Read Also

Field conditions in Ontario seen as ‘frustrating’

It continues to be a frustrating spring for field conditions through much of the province. Frequent precipitation has continued to…

The researchers are one of the first teams to win computing support from the new National Artificial Intelligence Research Resource Pilot in the United States.

The award will provide one million “node hours” of supercomputing time on the $60 million Frontera supercomputer at the Texas Advanced Computing Center at the University of Texas at Austin. Frontera’s power comes from more than 8,000 compute nodes, each containing 56 core processors. It’s the fastest supercomputer on a U.S. university campus.

The Iowa State researchers will use Frontera to help them train an ensemble of large machine learning models that can analyze photos to quickly identify agricultural pests, including insects and weeds. The models will be packaged into an app platform, which is designed to be deployed around the world to help farmers protect crops.

Future work will connect the vision models with tuned, large language models to provide a conversational tool that can suggest pest control strategies.

Professor Baskar Ganapathysubramanian at Iowa State is leading the computing project along with Aditya Balu, a data scientist at Iowa State’s Translational AI Center.

Ganapathysubramanian said the centre’s computing support enhances the research team’s ability to train, deploy and evaluate sophisticated AI models that enable profitable and sustainable agriculture.

The National Intelligence Research Resource Pilot, established in January as a two-year pilot program led by the National Science Foundation (NSF), announced the first 35 projects it will support by providing access to advanced computers.

Sethuraman Panchanathan, director of NSF, said the pilot is “fueled by the need to advance responsible AI research and broaden access to cutting-edge resources needed for AI research.”

At Iowa State, Ganapathysubramanian said researchers have been working on their approach for about two years with support from two federally funded efforts on campus. Those are the AI Institute for Resilient Agriculture; and Context Aware Learning for Sustainable Cyber-agricultural systems.

The original idea, conceptualized by Iowa State’s soynomics team, was to build AI tools to identify diseases in soybeans.

Ganapathysubramanian said the idea evolved to include identification of insects harmful to soybeans, then agricultural pests across Iowa, then agricultural pests around the world.

“The scope has been slowly broadening, and so have the computing requirements to develop our model,” he said.