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

Bridging the Gap Between Crop Breedi...

Skobalski, Juan Cruz,

Linked to FindBook

Google Book

Amazon

博客來

Bridging the Gap Between Crop Breeding and GeoAI: Soybean Yield Prediction From Multispectral UAV Images With Transfer Learning /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Bridging the Gap Between Crop Breeding and GeoAI: Soybean Yield Prediction From Multispectral UAV Images With Transfer Learning // Juan Cruz Skobalski.
Author:	Skobalski, Juan Cruz,
Description:	1 electronic resource (90 pages)
Notes:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
Subject:	Remote sensing. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30815501
ISBN:	9798382825724

Bridging the Gap Between Crop Breeding and GeoAI: Soybean Yield Prediction From Multispectral UAV Images With Transfer Learning /
Skobalski, Juan Cruz,

Bridging the Gap Between Crop Breeding and GeoAI: Soybean Yield Prediction From Multispectral UAV Images With Transfer Learning /Juan Cruz Skobalski. - 1 electronic resource (90 pages)

Source: Masters Abstracts International, Volume: 85-12.

Crop yield prediction using unmanned aerial vehicles imagery holds the promise of economizing crop breeding. Despite numerous publications towards crop yield prediction, existing research predominantly provides an on-site perspective, frequently missing the complexities of real-world applications. We tested different predictive modeling techniques for soybean yield in soybean trails from United States and Argentina as well as a combined dataset from both countries. We examine the efficacy of the Random Forest Regressor (RF), Gradient Boosting Regression (GB), and Deep Neural Networks (DNN) in forecasting yields across diverse geographic locations. A novel application of the Random Forest Classifier (RFC) is proposed for genotype selection, categorizing soybean yield potential. Furthermore, the research also studies the effect of temporal resolution on yield prediction, focusing on the critical development stages and optimal aerial survey frequencies for precise yield prediction. The study also pioneers the use of transfer learning for model adaptability in real-world breeding scenarios, training and transferring models within the four locations in Argentina, as well as training the model with the entire four locations on Argentina to predict the yield on the remaining United States locations. The culmination of these efforts offers actionable insights and strategies for the crop breeding community, aiming to facilitate improved decision-making and improve agricultural productivity. The combined dataset of Argentina and United States was the highest performance with an R2 of 0.76 using RF and GB algorithms. Our classification approach achieved the highest results also in the combination of both datasets, classifying accurately 73% of the high yielding genotypes. The temporal resolution study established that increasing the number of UAV flights to nine significantly improved yield prediction. Lastly, our study demonstrated that transfer learning yielded promising outcomes across trials within Argentina. However, the efficacy of transferring models from Argentina to the United States was limited, attributed to significant geo-specific variations.

English

ISBN: 9798382825724Subjects--Topical Terms:

535394
Remote sensing.
Subjects--Index Terms:

Machine learning

Bridging the Gap Between Crop Breeding and GeoAI: Soybean Yield Prediction From Multispectral UAV Images With Transfer Learning /
LDR:03687nmm a22004573i 4500 001 2438413
005 20260727132406.5
006 m o d
007 cr|nu||||||||
008 261011s2023 miu||||||m |||||||eng d
020 $a 9798382825724
035 $a (MiAaPQD)AAI30815501
035 $a AAI30815501
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Skobalski, Juan Cruz, $e author. $3 3829710
245 1 0 $a Bridging the Gap Between Crop Breeding and GeoAI: Soybean Yield Prediction From Multispectral UAV Images With Transfer Learning / $c Juan Cruz Skobalski.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (90 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: 85-12.
500 $a Advisors: Sagan, Vasit Committee members: Grignola, Fernando; Aydin, Orhun.
502 $b M.S. $c Saint Louis University $d 2023.
520 $a Crop yield prediction using unmanned aerial vehicles imagery holds the promise of economizing crop breeding. Despite numerous publications towards crop yield prediction, existing research predominantly provides an on-site perspective, frequently missing the complexities of real-world applications. We tested different predictive modeling techniques for soybean yield in soybean trails from United States and Argentina as well as a combined dataset from both countries. We examine the efficacy of the Random Forest Regressor (RF), Gradient Boosting Regression (GB), and Deep Neural Networks (DNN) in forecasting yields across diverse geographic locations. A novel application of the Random Forest Classifier (RFC) is proposed for genotype selection, categorizing soybean yield potential. Furthermore, the research also studies the effect of temporal resolution on yield prediction, focusing on the critical development stages and optimal aerial survey frequencies for precise yield prediction. The study also pioneers the use of transfer learning for model adaptability in real-world breeding scenarios, training and transferring models within the four locations in Argentina, as well as training the model with the entire four locations on Argentina to predict the yield on the remaining United States locations. The culmination of these efforts offers actionable insights and strategies for the crop breeding community, aiming to facilitate improved decision-making and improve agricultural productivity. The combined dataset of Argentina and United States was the highest performance with an R2 of 0.76 using RF and GB algorithms. Our classification approach achieved the highest results also in the combination of both datasets, classifying accurately 73% of the high yielding genotypes. The temporal resolution study established that increasing the number of UAV flights to nine significantly improved yield prediction. Lastly, our study demonstrated that transfer learning yielded promising outcomes across trials within Argentina. However, the efficacy of transferring models from Argentina to the United States was limited, attributed to significant geo-specific variations.
546 $a English
590 $a School code: 0193
650 4 $a Remote sensing. $3 535394
650 4 $a Agriculture. $3 518588
650 4 $a Geographic information science. $3 3432445
650 4 $a Plant sciences. $3 3173832
653 $a Machine learning
653 $a Multispectral imagery
653 $a Plant breeding
653 $a Soybean yield prediction
653 $a Transfer learning
690 $a 0370
690 $a 0799
690 $a 0473
690 $a 0800
690 $a 0479
710 2 $a Saint Louis University. $b Geoscience. $e degree granting institution. $3 3823062
720 1 $a Sagan, Vasit $e degree supervisor.
773 0 $t Masters Abstracts International $g 85-12.
790 $a 0193
791 $a M.S.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30815501