Scientists Stack Six Algorithms to Improve Predictions of Yield-Boosting Crop Traits

To help researchers identify high yielding crop traits, a team from the University of Illinois have stacked together six high-powered, machine learning algorithms that are used to interpret hyperspectral data. The team showed that the technique improved the predictive power of a previous study by up to 15 percent, compared to using just one algorithm.

A previous study by the team introduced spectral analysis as a means to quickly identify photosynthetic improvements that could increase yields. In a new study, published in Frontiers in Plant Science, the team improved their previous predictions of photosynthetic capacity by as much as 15 percent using machine learning, where computers automatically applied these six algorithms to their dataset without human help.

"We are empowering scientists from many fields, who are not necessarily experts in computational analysis, to translate their enormous datasets into beneficial results," said first author Peng Fu, a postdoctoral researcher at Illinois, who led the work for the project Realizing Increased Photosynthetic Efficiency (RIPE). He added that with the stacked algorithm, "scientists do not need to scratch their heads" to figure out which machine learning algorithms to use as they can apply six or more algorithms—for the price of one—to make more accurate predictions.

For more details, read the news article in the University of Illinois website.

Figure: A team from the University of Illinois has stacked together six high-powered algorithms to help researchers make more precise predictions from hyperspectral data to identify high-yielding crop traits. From left to right: Postdoctoral Researcher Peng Fu, USDA-ARS Scientist Carl Bernacchi, Postdoctoral Researcher Katherine Meacham-Hensold, and Assistant Professor Kaiyu Guan.