Research Article | Open Access

Volume 2022 |Article ID 9879610 | https://doi.org/10.34133/2022/9879610

Objective Phenotyping of Root System Architecture Using Image Augmentation and Machine Learning in Alfalfa (Medicago sativa L.)

Zhanyou Xu iD ,¹ Larry M. York iD ,² Anand SeethepalliiD ,³ Bruna Bucciarelli,⁴ Hao Cheng,⁵ and Deborah A. Samac¹

¹USDA-ARS, Plant Science Research Unit, 1991 Upper Buford Circle, St. Paul, MN 55108, USA
²Biosciences Division and Center for Bioenergy Innovation, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA
³Noble Research Institute, LLC, Ardmore, OK 73401, USA
⁴Department of Agronomy and Plant Genetics, University of Minnesota, 1991 Upper Buford Circle, St. Paul, MN 55108, USA
⁵Department of Animal Science, University of California, 2251 Meyer Hall, One Shields Ave., Davis, CA 95616, USA

Abstract

Active breeding programs specifically for root system architecture (RSA) phenotypes remain rare; however, breeding for branch and taproot types in the perennial crop alfalfa is ongoing. Phenotyping in this and other crops for active RSA breeding has mostly used visual scoring of specific traits or subjective classification into different root types. While image-based methods have been developed, translation to applied breeding is limited. This research is aimed at developing and comparing image-based RSA phenotyping methods using machine and deep learning algorithms for objective classification of 617 root images from mature alfalfa plants collected from the field to support the ongoing breeding efforts. Our results show that unsupervised machine learning tends to incorrectly classify roots into a normal distribution with most lines predicted as the intermediate root type. Encouragingly, random forest and TensorFlow-based neural networks can classify the root types into branch-type, taproot-type, and an intermediate taproot-branch type with 86% accuracy. With image augmentation, the prediction accuracy was improved to 97%. Coupling the predicted root type with its prediction probability will give breeders a confidence level for better decisions to advance the best and exclude the worst lines from their breeding program. This machine and deep learning approach enables accurate classification of the RSA phenotypes for genomic breeding of climate-resilient alfalfa.