RALEIGH, N.C. — Researchers at North Carolina State University will use a grant from Schmidt Sciences to develop an AI-enabled open-source platform that can analyze the potential to convert agricultural residues (biomass such as misshapen sweet potatoes and discarded green tops) into biofuels and other bioproducts, creating new business opportunities.
The four-year project, Resource Engineering Framework for Responsible, Augmented Modeling and Engagement (REFRAME), supports the path to a circular bioeconomy that reuses biomass to create new materials. This approach reduces waste, creates opportunities for entrepreneurs, and provides new sources of income for farmers and agribusinesses.
For example, to find the best way to convert sweet potatoes and green tops into biofuels, sustainable aviation fuel companies will be able to use the new platform to analyze current yields in their region and decide on locations for collection facilities and biorefineries. The platform is designed to support decision-making for farmers, processing plants, researchers, and policy makers.
Daniella Jones of North Carolina State University will lead the project. She is an assistant professor in the Department of Bioagricultural Engineering, a joint faculty member with the Idaho National Laboratory, and director of the NC Plant Science Initiative's Education and Workforce Development Platform. REFRAME co-leaders are Debjani Sihi from North Carolina State University's Department of Plant and Microbial Biology, Joe Sagues from the Department of Bioagricultural Engineering, and Cranos Williams from the Department of Electrical and Computer Engineering. Additional collaborators include the Idaho National Laboratory, the University of Illinois at Urbana-Champaign, ICF International, and McCarl & Associates.
We asked lead researcher Jones to explain the team's plans for REFRAME.
How do you approach the REFRAME project?
My specialty is supply chain analysis. Our efforts therefore cover the entire supply chain. So where is this agricultural biomass in terms of availability? How do we get it from point A to point B in terms of accessibility? How can we characterize it? What are its attributes? What does the transformation make of it? How much does it cost? What are the impacts and shocks of new products being introduced to the market? How will farmers respond? How will biomanufacturing impact land use? These are examples of questions we want to be able to answer more quickly using AI-enabled platforms.
Do you plan to incorporate existing digital models and tools?
For all these supply chain components, we identified several legacy models, models that have been developed for many years in open source and have addressed one aspect of the supply chain, such as agricultural models that analyze the availability of biomass. However, these legacy models have always operated in silos. Although many people have worked hard on one model, there is currently no strong connection between the models. Pipelines wait for delivery until the output of one model is input as input to another model, which can take months or years.
How do you apply AI to solve these problems?
What we're creating is, first of all, a digital backbone. This is a digital environment that can store and retain the computing power to run models multiple times so that much faster AI surrogates can be created. By creating simplified versions of these models that run faster, we may be able to make predictions that were previously not possible with traditional models. That's the point. We're creating a pipeline of this model and making it accessible to everyone as an AI-powered open source platform.
The REFRAME project is part of Schmidt Sciences' Virtual Institute on Future Materials (VIFF).
About Schmidt Science
Schmidt Sciences is a nonprofit organization founded in 2024 by Eric Schmidt and Wendy Schmidt that is committed to advancing scientific knowledge and breakthroughs using the most promising and advanced tools to support our planet's prosperity. The organization prioritizes research in areas with the potential for high impact, including AI and advanced computing, astrophysics, biological sciences, climate and space, and supports researchers in a variety of fields through its Science Systems Program.
Originally published on CALS News
–D’Lyn Ford, North Carolina State University
