Penn State AI model detects crop stress with fewer computations
Researchers at Penn State developed a new artificial intelligence model that detects agricultural crop stress using less computing power than existing methods.
Model uses three processing pathways
The new system named PSUMamba analyzes spectral information to identify biochemical changes in crops. A second pathway examines conditions over time while a third analyzes spatial features within images. These three pathways combine to improve the ability to identify stress accurately. The team tested this technology on white button mushrooms located in a greenhouse facility.
Testing addresses industry challenges
Pennsylvania grows 74 percent of the nations Agaricus mushrooms according to the U.S. Department of Agriculture. National mushroom sales fell 16 percent to $922 million during the last season. Postharvest quality degradation represents a significant challenge for this economically important industry. The researchers subjected mushrooms to thermal shock and microwave radiation to simulate stress.
Results published in Scientific Reports
Study senior author Shirin Ghatrehsamani is an assistant professor of agricultural and biological engineering. First author Weiqun Wang is a doctoral candidate in the same department. The findings were recently published in the journal Scientific Reports. Capturing subtle physiological shifts well before they are seen by the human eye is what hyperspectral imaging achieves.
Reported by one outlet
Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.
Reported by
1 independent outlet. Headline as published. Links open the original report.