Artificial intelligence is reshaping the frontiers of science. In the College of Science, researchers are applying AI in bold, creative ways — not to replace scientific inquiry, but to amplify it. Across disciplines, our scientists are using artificial intelligence to tackle urgent questions in health, agriculture and the environment. Their work contributes to Oregon State’s broader goal to apply AI in ways that are ethical, responsible and transformative. From decoding the mysteries of the gut-brain axis to improving farming techniques, AI is accelerating the pace of discovery. By integrating machine learning with core scientific expertise, our researchers are uncovering new insights, enhancing the reliability of data and scaling up solutions to complex global problems. At its best, AI doesn’t replace human judgment — it expands what’s possible when thoughtful scientists and powerful tools work together in pursuit of impact. Helping Oregon farmers with smarter seed-testing solutions Statistician Yanming Di is working to modernize an outdated system for seed purity analysis. The Willamette Valley, known as the “grass seed capital of the world,” produces more than 90% of the grass seed used in the United States and a significant portion of the global supply. Managing the region’s 500 million pounds of grass seed annually presents challenges — especially outdated testing methods and tools. A multidisciplinary research group is combining expertise in robotics, artificial intelligence, computer science, statistics and crop science to create a modern solution for an old system. Their goal: a system for real-time, onsite seed purity analysis that could reduce waste and improve seed quality for growers. Determined by the amount of weed seeds, unwanted crops and inert materials, seed lot quality impacts every stage of agriculture. Currently, trained technicians spend years learning to identify up to 200 seed species and growers must constantly pause operations to test seed lots, balancing quality control and profitability. Supported by $255K of grants from the USDA, the Oregon Grass Seed Commissions and the OSU College of Agricultural Sciences, the team is working to automate this process. The first challenge is capturing highquality images of seeds to train the computer to see the differences. Next, it’s figuring out how to maintain consistent conditions while they’re training and testing because if those conditions change, what’s used for training may not apply to testing. Statisticians like Di are needed to calculate levels of uncertainty, while computer scientists will provide feedback on the neural networks used by AI to perform tasks that typically require human intelligence. In the 21st century, the boundary between statistics and AI has started to blur, with both fields analyzing data and trying to make sense of it. “I don’t really think too much about which area I’m working on, whether it’s AI or statistics,” Di said. “I believe on this team, we just focus on solving the problem.” By applying cutting-edge science to the needs of local stakeholders, the team is turning a centuries-old challenge into an opportunity for multidisciplinary innovation. “A land grant university is bringing together people with diverse backgrounds and skills to help the people within Oregon. And that is essentially the entire mission of land grant universities,” said OSU Director of Seed Services and collaborator Dan Curry. This collaborative effort underscores the power of science and highlights the commitment of Oregon State to helping Oregonians thrive. “I don’t really think too much about whether it’s AI or statistics. We just focus on solving the problem.” IMPACT FALL 2025 9
RkJQdWJsaXNoZXIy MTcxMjMwNg==