Next Article in Journal
Developing a New Machine-Learning Algorithm for Estimating Chlorophyll-a Concentration in Optically Complex Waters: A Case Study for High Northern Latitude Waters by Using Sentinel 3 OLCI
Previous Article in Journal
AdTree: Accurate, Detailed, and Automatic Modelling of Laser-Scanned Trees
Previous Article in Special Issue
Extending Hyperspectral Imaging for Plant Phenotyping to the UV-Range
Open AccessArticle

Estimation of the Maturity Date of Soybean Breeding Lines Using UAV-Based Multispectral Imagery

1
Division of Food Systems and Bioengineering, University of Missouri, Columbia, MO 65211, USA
2
Division of Plant Sciences, University of Missouri, Columbia, MO 65211, USA
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(18), 2075; https://doi.org/10.3390/rs11182075
Received: 6 August 2019 / Revised: 28 August 2019 / Accepted: 2 September 2019 / Published: 4 September 2019
(This article belongs to the Special Issue Advanced Imaging for Plant Phenotyping)
Physiological maturity date is a critical parameter for the selection of breeding lines in soybean breeding programs. The conventional method to estimate the maturity dates of breeding lines uses visual ratings based on pod senescence by experts, which is subjective by human estimation, labor-intensive and time-consuming. Unmanned aerial vehicle (UAV)-based phenotyping systems provide a high-throughput and powerful tool of capturing crop traits using remote sensing, image processing and machine learning technologies. The goal of this study was to investigate the potential of predicting maturity dates of soybean breeding lines using UAV-based multispectral imagery. Maturity dates of 326 soybean breeding lines were taken using visual ratings from the beginning maturity stage (R7) to full maturity stage (R8), and the aerial multispectral images were taken during this period on 27 August, 14 September and 27 September, 2018. One hundred and thirty features were extracted from the five-band multispectral images. The maturity dates of the soybean lines were predicted and evaluated using partial least square regression (PLSR) models with 10-fold cross-validation. Twenty image features with importance to the estimation were selected and their changing rates between each two of the data collection days were calculated. The best prediction (R2 = 0.81, RMSE = 1.4 days) was made by the PLSR model using image features taken on 14 September and their changing rates between 14 September and 27 September with five components, leading to the conclusion that the UAV-based multispectral imagery is promising and practical in estimating maturity dates of soybean breeding lines. View Full-Text
Keywords: machine learning; maturity date; multispectral image; soybean breeding; UAV-based phenotyping machine learning; maturity date; multispectral image; soybean breeding; UAV-based phenotyping
Show Figures

Graphical abstract

MDPI and ACS Style

Zhou, J.; Yungbluth, D.; Vong, C.N.; Scaboo, A.; Zhou, J. Estimation of the Maturity Date of Soybean Breeding Lines Using UAV-Based Multispectral Imagery. Remote Sens. 2019, 11, 2075.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop