|
|
Registros recuperados : 1 | |
Registros recuperados : 1 | |
|
|
Registro completo
|
Biblioteca (s) : |
INIA La Estanzuela. |
Fecha actual : |
05/11/2020 |
Actualizado : |
05/09/2022 |
Tipo de producción científica : |
Artículos en Revistas Indexadas Internacionales |
Circulación / Nivel : |
Internacional - -- |
Autor : |
TREVISAN, R.; PÉREZ, O.; SCHMITZ, N.; DIERS, B.; MARTIN, N |
Afiliación : |
RODRIGO TREVISAN, Department of Crop Sciences, University of Illinois at Urbana Champaign, Urbana, IL 61801, USA.; OSVALDO MARTIN PEREZ GONZALEZ, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; NATHAN SCHMITZ, GDM Seeds Inc., Gibson City, IL 60936, USA.; BRIAN DIERS, Department of Crop Sciences, University of Illinois at Urbana Champaign, Urbana, IL 61801, USA.; NICOLAS MARTIN, Department of Crop Sciences, University of Illinois at Urbana Champaign, Urbana, IL 61801, USA. |
Título : |
High-throughput phenotyping of soybean maturity using time Series UAV imagery and convolutional neural networks. |
Fecha de publicación : |
2020 |
Fuente / Imprenta : |
Remote Sensing, 2020, 12(21), 3617. OPEN ACCESS. DOI: https://doi.org/10.3390/rs12213617. |
DOI : |
10.3390/rs12213617 |
Idioma : |
Inglés |
Notas : |
Article history: Received: 18 September 2020 / Revised: 28 October 2020 / Accepted: 29 October 2020 / Published: 4 November 2020. |
Contenido : |
Abstract: Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges.Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies
have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were
developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture developed solves limitations of previous research and can be used at scale in commercial breeding programs. MenosAbstract: Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges.Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies
have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were
developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture developed solves limitations of previ... Presentar Todo |
Palabras claves : |
GLYCINE MAX (L.) MERR; MACHINE LEARNING; PHYSIOLOGICAL MATURITY; PLANT BREEDING; SOYBEAN PHENOLOGY. |
Thesagro : |
MEJORAMIENTO GENETICO DE PLANTAS; SOJA. |
Asunto categoría : |
F30 Genética vegetal y fitomejoramiento |
URL : |
http://www.ainfo.inia.uy/digital/bitstream/item/14789/1/remotesensing-12-03617.pdf
https://www.mdpi.com/2072-4292/12/21/3617/htm#
|
Marc : |
LEADER 02555naa a2200277 a 4500 001 1061456 005 2022-09-05 008 2020 bl uuuu u00u1 u #d 024 7 $a10.3390/rs12213617$2DOI 100 1 $aTREVISAN, R. 245 $aHigh-throughput phenotyping of soybean maturity using time Series UAV imagery and convolutional neural networks.$h[electronic resource] 260 $c2020 500 $aArticle history: Received: 18 September 2020 / Revised: 28 October 2020 / Accepted: 29 October 2020 / Published: 4 November 2020. 520 $aAbstract: Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges.Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture developed solves limitations of previous research and can be used at scale in commercial breeding programs. 650 $aMEJORAMIENTO GENETICO DE PLANTAS 650 $aSOJA 653 $aGLYCINE MAX (L.) MERR 653 $aMACHINE LEARNING 653 $aPHYSIOLOGICAL MATURITY 653 $aPLANT BREEDING 653 $aSOYBEAN PHENOLOGY 700 1 $aPÉREZ, O. 700 1 $aSCHMITZ, N. 700 1 $aDIERS, B. 700 1 $aMARTIN, N 773 $tRemote Sensing, 2020, 12(21), 3617. OPEN ACCESS. DOI: https://doi.org/10.3390/rs12213617.
Descargar
Esconder MarcPresentar Marc Completo |
Registro original : |
INIA La Estanzuela (LE) |
|
Biblioteca
|
Identificación
|
Origen
|
Tipo / Formato
|
Clasificación
|
Cutter
|
Registro
|
Volumen
|
Estado
|
Volver
|
No hay resultados para la expresión de búsqueda informada registros. |
|
|