Imaging, ML Methods Speed Effort to Reduce Crops' Need for Water

New imaging and machine learning (ML) tools developed by University of Illinois at Urbana-Champaign (U of I) scientists can analyze the genomic features of plant leaves as a means of increasing water-use efficiency for crops.

The team analyzed lighter green pores (stomata) on leaves of corn, sorghum, and grasses of the genus Setaria to determine their role in water-use efficiency during photosynthesis.

U of I's Jiayang Xie repurposed an ML tool designed to help driverless cars navigate complex environments into an application that could rapidly identify, count, and measure thousands of cells and cell features in each leaf sample.

According to U of I’s Andrew Leakey, the researchers found “the size and shape of the stomata in corn appeared to be more important than had previously been recognized,” which will inform future efforts to breed crops that use water more efficiently.

From University of Illinois News Bureau
View Full Article

Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA