In the realm of agricultural innovation, a study conducted by the University of Illinois Urbana-Champaign has shed light on the advancement of sweet potato quality assessment. This research, a collaborative effort involving the U.S. Department of Agriculture and universities across Mississippi, North Carolina, Michigan, Louisiana, and Illinois, leverages hyperspectral imaging and explainable artificial intelligence (AI) to evaluate sweet potato attributes. The focus is on determining dry matter, firmness, and soluble sugar content; key factors influencing market value and suitability for consumption or processing.
Mohammed Kamruzzaman, an assistant professor at the Department of Agricultural and Biological Engineering, highlighted the efficiency of hyperspectral imaging over traditional laboratory methods. "Traditionally, quality assessment is done using laboratory analytical methods. You need different instruments to measure different attributes in the lab, and you need to wait for the results. With hyperspectral imaging, you can measure several parameters simultaneously. You can assess every potato in a batch, not just a few samples." This technique not only promises a non-invasive, swift, and cost-effective approach but also circumvents the limitations of conventional quality assessment by processing a vast amount of data through machine learning.
The study's application of a visible near-infrared hyperspectral imaging camera, capturing images from multiple angles for spectral data analysis, represents a significant stride towards a more transparent and explainable AI in the field of agricultural research. By identifying key wavelengths and developing color maps, the researchers aim to streamline the process of sweet potato quality assessment, enhancing both producer and consumer satisfaction.
Source: phys.org