Researcher gets $150,000 grant to use AI for Salmonella detection in onions

A researcher at Southern Illinois University-Carbondale is working on using artificial intelligence (AI) to detect the deadly pathogen Salmonella before it ever enters the food supply.

Anas Alsobeh, assistant professor of information technology, recently received a $150,000 grant from the USDA’s National Institute of Food and Agriculture to develop an AI-based rapid detection method for finding Salmonella in onions. The system combines microscopic imaging with AI, which compares samples to a large-scale dataset containing images of bacterial microcolonies at early stages of growth.

The technology integrates convolutional neural networks that can automatically detect the presence of the bacteria. The grant also funds hands-on workshops to train stakeholders on using intelligent imaging in food inspection processes.

“While the project is still underway, we anticipate the optimized AI detection system will enable rapid, nondestructive Salmonella screening,” Alsobeh said. “Early validation of the technology showed promise in real-time microbial detection, with potential benefits for cost-effective, high-volume food safety applications across the industry.”

This innovative approach aligns with a growing optimism within the food safety community about the role of AI. Researchers at the University of California-Davis have also explored how AI can enhance food safety, demonstrating that techniques using AI and optical imaging can quickly and accurately identify harmful bacteria in food. Luyao Ma, a researcher involved in that study, emphasized that food scientists are beginning to leverage AI to transform the agricultural food system, paving the way for higher levels of food safety.

“Food safety is an essential part of the food business, so if we can strengthen that area by providing a cost-effective, rapid, highly sensitive, and specific approach, I think it will give consumers more confidence in our food systems as we move forward,” said Nitin Nitin, professor of food science and technology at UC Davis.

Using methods like Alsobeh’s, researchers have found that rapid screening can significantly reduce the time required to detect bacterial contamination — from the standard 5 to 7 days to just a few hours. This not only ensures timely interventions to prevent foodborne illness outbreaks but also reduces the economic burden associated with food recalls and liability.

Work on Alsobeh’s project began in August 2024 and is set to conclude in July 2026. He earned his doctorate in computer science from Utah State University in 2015, and his research interests include software design and modeling, data analysis, web technology, security analysis, machine learning and cloud computing.

The advancement of AI in food safety presents both opportunities and challenges. As the food industry continues to evolve, the potential for automated food safety inspections grows, promising a future where the risk of contamination can be mitigated through innovative technology. However, experts emphasize the importance of combining these new tools with established food safety practices to ensure comprehensive protection against foodborne pathogens.

(To sign up for a free subscription to Food Safety News, click here.)