東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Optimizing Soybean Breeding With Hig...

Blair, Samuel Wayne,

Linked to FindBook

Google Book

Amazon

博客來

Optimizing Soybean Breeding With High-Throughput Digital Phenotyping Methods for Relative Maturity and Yield Prediction /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Optimizing Soybean Breeding With High-Throughput Digital Phenotyping Methods for Relative Maturity and Yield Prediction // Samuel Wayne Blair.
Author:	Blair, Samuel Wayne,
Description:	1 electronic resource (87 pages)
Notes:	Source: Masters Abstracts International, Volume: 86-12.
Contained By:	Masters Abstracts International86-12.
Subject:	Plant sciences. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31840908
ISBN:	9798286429578

Optimizing Soybean Breeding With High-Throughput Digital Phenotyping Methods for Relative Maturity and Yield Prediction /
Blair, Samuel Wayne,

Optimizing Soybean Breeding With High-Throughput Digital Phenotyping Methods for Relative Maturity and Yield Prediction /Samuel Wayne Blair. - 1 electronic resource (87 pages)

Source: Masters Abstracts International, Volume: 86-12.

High-throughput phenotyping (HTP) is an emerging field providing plant breeding programs with advanced tools for more efficient and precise data collection. UAV systems enable rapid field scouting and can carry a range of sensors for versatile data collection, while ground-based robots offer high-resolution imaging beneath the plant canopy, capturing details UAVs often miss.Together, these HTP systems streamline breeding processes, conserving resources that would otherwise be dedicated to manual tasks.Accurately determining the maturity of soybean cultivars is essential for maximizing their yield potential. We introduce an automated soybean relative maturity classification system using convolutional neural networks (CNNs) with UAV imagery. This system extracts plot color change over time to create a two-dimensional hue histogram, which is used to train a CNN model for automated classification of soybean maturity. We also look into the number of UAV time points needed to achieve accurate classifications. Additionally, we examine how the rate of greenness loss relates to soybean maturity and yield, offering insights into potential additional selection criteria for breeding.While UAV systems offer a great tool for quick scouting of a breeding field, they often lack the resolution needed to observe smaller plant features critical for yield estimation, such as soybean pods and seeds. We present a HTP method for estimating soybean seed yield by using ground robot video. This video-turned-imagery data is then used in conjunction with ML tools to detect and quantify soybean seeds. This is then used to estimate and rank soybean plot yield.The benefits of remote sensing and HTP techniques give breeding programs the ability to assign critical labor and resources to other tasks. Unlike traditional large equipment, UAVs and ground robots are generally easier to operate, requiring less specialized training and minimizing the logistical challenges of transporting heavy machinery. UAVs offer the flexibility to cover large areas quickly without the need for extensive setup, while ground robots can navigate fields and collect detailed data without disturbing the plants. Maturity data collection is a highly laborious task and can take multiple weeks to accomplish. Similarly, yield data collection requires specialized equipment training and is logistically challenging. Utilizing ML tools with UAV and ground robot systems can save countless labor hours and equipment breakdown costs.

English

ISBN: 9798286429578Subjects--Topical Terms:

3173832
Plant sciences.
Subjects--Index Terms:

Convolutional neural networks

Optimizing Soybean Breeding With High-Throughput Digital Phenotyping Methods for Relative Maturity and Yield Prediction /
LDR:03987nmm a22004333i 4500 001 2435767
005 20251029060346.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798286429578
035 $a (MiAaPQD)AAI31840908
035 $a AAI31840908
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Blair, Samuel Wayne, $e author. $3 3826188
245 1 0 $a Optimizing Soybean Breeding With High-Throughput Digital Phenotyping Methods for Relative Maturity and Yield Prediction / $c Samuel Wayne Blair.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (87 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-12.
500 $a Advisors: Singh, Asheesh K. Committee members: Singh, Arti; Sarkar, Soumik; Ganapathysubramanian, Baskar.
502 $b M.S. $c Iowa State University $d 2025.
520 $a High-throughput phenotyping (HTP) is an emerging field providing plant breeding programs with advanced tools for more efficient and precise data collection. UAV systems enable rapid field scouting and can carry a range of sensors for versatile data collection, while ground-based robots offer high-resolution imaging beneath the plant canopy, capturing details UAVs often miss.Together, these HTP systems streamline breeding processes, conserving resources that would otherwise be dedicated to manual tasks.Accurately determining the maturity of soybean cultivars is essential for maximizing their yield potential. We introduce an automated soybean relative maturity classification system using convolutional neural networks (CNNs) with UAV imagery. This system extracts plot color change over time to create a two-dimensional hue histogram, which is used to train a CNN model for automated classification of soybean maturity. We also look into the number of UAV time points needed to achieve accurate classifications. Additionally, we examine how the rate of greenness loss relates to soybean maturity and yield, offering insights into potential additional selection criteria for breeding.While UAV systems offer a great tool for quick scouting of a breeding field, they often lack the resolution needed to observe smaller plant features critical for yield estimation, such as soybean pods and seeds. We present a HTP method for estimating soybean seed yield by using ground robot video. This video-turned-imagery data is then used in conjunction with ML tools to detect and quantify soybean seeds. This is then used to estimate and rank soybean plot yield.The benefits of remote sensing and HTP techniques give breeding programs the ability to assign critical labor and resources to other tasks. Unlike traditional large equipment, UAVs and ground robots are generally easier to operate, requiring less specialized training and minimizing the logistical challenges of transporting heavy machinery. UAVs offer the flexibility to cover large areas quickly without the need for extensive setup, while ground robots can navigate fields and collect detailed data without disturbing the plants. Maturity data collection is a highly laborious task and can take multiple weeks to accomplish. Similarly, yield data collection requires specialized equipment training and is logistically challenging. Utilizing ML tools with UAV and ground robot systems can save countless labor hours and equipment breakdown costs.
546 $a English
590 $a School code: 0097
650 4 $a Plant sciences. $3 3173832
650 4 $a Biology. $3 522710
650 4 $a Bioinformatics. $3 553671
650 4 $a Genetics. $3 530508
653 $a Convolutional neural networks
653 $a Ground robots
653 $a Soybean maturity
653 $a Uncrewed aerial systems
690 $a 0479
690 $a 0306
690 $a 0369
690 $a 0715
710 2 $a Iowa State University. $b Agronomy. $e degree granting institution. $3 3826189
720 1 $a Singh, Asheesh K. $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-12.
790 $a 0097
791 $a M.S.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31840908