Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery

Abstract Global crop production is facing the challenge of a high projected demand, while the yields of major crops are not increasing at sufficient speeds. Crop breeding is an important way to boost crop productivity, however its improvement rate is partially hindered by the long crop generation cy...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wenan Yuan, Nuwan Kumara Wijewardane, Shawn Jenkins, Geng Bai, Yufeng Ge, George L. Graef
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2019
Materias:
R
Q
Acceso en línea:https://doaj.org/article/20981ad85a1d4a869b8d3f32a73a9051
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:20981ad85a1d4a869b8d3f32a73a9051
record_format dspace
spelling oai:doaj.org-article:20981ad85a1d4a869b8d3f32a73a90512021-12-02T15:08:20ZEarly Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery10.1038/s41598-019-50480-x2045-2322https://doaj.org/article/20981ad85a1d4a869b8d3f32a73a90512019-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-50480-xhttps://doaj.org/toc/2045-2322Abstract Global crop production is facing the challenge of a high projected demand, while the yields of major crops are not increasing at sufficient speeds. Crop breeding is an important way to boost crop productivity, however its improvement rate is partially hindered by the long crop generation cycles. If end-season crop traits such as yield can be predicted through early-season phenotypic measurements, crop selection can potentially be made before a full crop generation cycle finishes. This study explored the possibility of predicting soybean end-season traits through the color and texture features of early-season canopy images. Six thousand three hundred and eighty-three images were captured at V4/V5 growth stage over 6039 soybean plots growing at four locations. One hundred and forty color features and 315 gray-level co-occurrence matrix-based texture features were derived from each image. Another two variables were also introduced to account for location and timing differences between the images. Five regression and five classification techniques were explored. Best results were obtained using all 457 predictor variables, with Cubist as the regression technique and Random Forests as the classification technique. Yield (RMSE = 9.82, R2 = 0.68), Maturity (RMSE = 3.70, R2 = 0.76) and Seed Size (RMSE = 1.63, R2 = 0.53) were identified as potential soybean traits that might be early predictable.Wenan YuanNuwan Kumara WijewardaneShawn JenkinsGeng BaiYufeng GeGeorge L. GraefNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-17 (2019)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Wenan Yuan
Nuwan Kumara Wijewardane
Shawn Jenkins
Geng Bai
Yufeng Ge
George L. Graef
Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery
description Abstract Global crop production is facing the challenge of a high projected demand, while the yields of major crops are not increasing at sufficient speeds. Crop breeding is an important way to boost crop productivity, however its improvement rate is partially hindered by the long crop generation cycles. If end-season crop traits such as yield can be predicted through early-season phenotypic measurements, crop selection can potentially be made before a full crop generation cycle finishes. This study explored the possibility of predicting soybean end-season traits through the color and texture features of early-season canopy images. Six thousand three hundred and eighty-three images were captured at V4/V5 growth stage over 6039 soybean plots growing at four locations. One hundred and forty color features and 315 gray-level co-occurrence matrix-based texture features were derived from each image. Another two variables were also introduced to account for location and timing differences between the images. Five regression and five classification techniques were explored. Best results were obtained using all 457 predictor variables, with Cubist as the regression technique and Random Forests as the classification technique. Yield (RMSE = 9.82, R2 = 0.68), Maturity (RMSE = 3.70, R2 = 0.76) and Seed Size (RMSE = 1.63, R2 = 0.53) were identified as potential soybean traits that might be early predictable.
format article
author Wenan Yuan
Nuwan Kumara Wijewardane
Shawn Jenkins
Geng Bai
Yufeng Ge
George L. Graef
author_facet Wenan Yuan
Nuwan Kumara Wijewardane
Shawn Jenkins
Geng Bai
Yufeng Ge
George L. Graef
author_sort Wenan Yuan
title Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery
title_short Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery
title_full Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery
title_fullStr Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery
title_full_unstemmed Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery
title_sort early prediction of soybean traits through color and texture features of canopy rgb imagery
publisher Nature Portfolio
publishDate 2019
url https://doaj.org/article/20981ad85a1d4a869b8d3f32a73a9051
work_keys_str_mv AT wenanyuan earlypredictionofsoybeantraitsthroughcolorandtexturefeaturesofcanopyrgbimagery
AT nuwankumarawijewardane earlypredictionofsoybeantraitsthroughcolorandtexturefeaturesofcanopyrgbimagery
AT shawnjenkins earlypredictionofsoybeantraitsthroughcolorandtexturefeaturesofcanopyrgbimagery
AT gengbai earlypredictionofsoybeantraitsthroughcolorandtexturefeaturesofcanopyrgbimagery
AT yufengge earlypredictionofsoybeantraitsthroughcolorandtexturefeaturesofcanopyrgbimagery
AT georgelgraef earlypredictionofsoybeantraitsthroughcolorandtexturefeaturesofcanopyrgbimagery
_version_ 1718388172777324544