國立虎尾科技大學 |

Application of UAS-Based Remote Sensing in Estimating Crop Phenotypic Traits.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Application of UAS-Based Remote Sensing in Estimating Crop Phenotypic Traits./
Author:	Hassani, Kianoosh.
Description:	1 online resource (102 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-07, Section: B.
Contained By:	Dissertations Abstracts International85-07B.
Subject:	Remote sensing. -
Online resource:	click for full text (PQDT)
ISBN:	9798381302714

Application of UAS-Based Remote Sensing in Estimating Crop Phenotypic Traits.
Hassani, Kianoosh.

Application of UAS-Based Remote Sensing in Estimating Crop Phenotypic Traits. - 1 online resource (102 pages)

Source: Dissertations Abstracts International, Volume: 85-07, Section: B.

Thesis (Ph.D.)--Oklahoma State University, 2023.

Includes bibliographical references

Traditional field-based methods for monitoring crop phenotypic traits-defined as structural and biochemical characteristics and their variability during plant life cycle-are costly and limited in their ability to cover large spatial extents. Therefore, I aimed to test the application of unoccupied aerial systems (UAS) in monitoring crop traits. I designed two experiments to achieve two objectives: (1) assess the ability of UAS-derived metrics in estimating nitrogen (N) content, yield, and several structural traits, including leaf area index (LAI), plant height, fresh and dry biomass, and yield over the growing season and (2) determine the impact of spatial and spectral resolution on retrieval accuracy of N content. While both experiments took place in Stillwater, Oklahoma, U.S., experiment 1 was conducted on winter wheat while experiment 2 was conducted on corn and sorghum. To achieve the objectives, I used an UAS system to collect multispectral imagery, a spectroradiometer to collect non-imaging hyperspectral data, and conducted field campaigns to harvest foliage samples for trait quantification. In terms of methodology, I used a suite of vegetation indices (VIs) and machine learning algorithms (MLAs) to estimate crop traits. My findings provided evidence that relatively simple VIs, as opposed to complex MLAs, can be reliably used for estimating crop traits and yield. This is an important finding in the context of crop monitoring as developing MLAs requires multiple extensive in-situ data collection campaigns. Further, results showed that UAS data with coarse spectral resolution had similar performance at estimating crop traits when compared to our spectroradiometer data with fine spectral resolution. In addition, UAS data with pixel sizes ranging from 1 cm to 1 m had similar performance in terms of correlation coefficient (r) and root mean square (RMSE) at estimating N content, suggesting that data with spatial resolution of approximately 1 m might be sufficient for monitoring crop traits. Overall, these findings can potentially aid breeders through providing rapid and non-destructive proxies of crop phenotypic traits. Moreover, my findings indicate the possibility of developing cheaper spectral monitoring instruments without sacrificing prediction accuracy of crop traits.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381302714Subjects--Topical Terms:

557272
Remote sensing.
Subjects--Index Terms:

Machine learning algorithmIndex Terms--Genre/Form:

554714
Electronic books.

Application of UAS-Based Remote Sensing in Estimating Crop Phenotypic Traits.
LDR:03770ntm a22004097 4500 001 1144832
005 20240611104929.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381302714
035 $a (MiAaPQ)AAI30568885
035 $a AAI30568885
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Hassani, Kianoosh. $3 1469987
245 1 0 $a Application of UAS-Based Remote Sensing in Estimating Crop Phenotypic Traits.
264 0 $c 2023
300 $a 1 online resource (102 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: Dissertations Abstracts International, Volume: 85-07, Section: B.
500 $a Advisor: Gholizadeh, Hamed.
502 $a Thesis (Ph.D.)--Oklahoma State University, 2023.
504 $a Includes bibliographical references
520 $a Traditional field-based methods for monitoring crop phenotypic traits-defined as structural and biochemical characteristics and their variability during plant life cycle-are costly and limited in their ability to cover large spatial extents. Therefore, I aimed to test the application of unoccupied aerial systems (UAS) in monitoring crop traits. I designed two experiments to achieve two objectives: (1) assess the ability of UAS-derived metrics in estimating nitrogen (N) content, yield, and several structural traits, including leaf area index (LAI), plant height, fresh and dry biomass, and yield over the growing season and (2) determine the impact of spatial and spectral resolution on retrieval accuracy of N content. While both experiments took place in Stillwater, Oklahoma, U.S., experiment 1 was conducted on winter wheat while experiment 2 was conducted on corn and sorghum. To achieve the objectives, I used an UAS system to collect multispectral imagery, a spectroradiometer to collect non-imaging hyperspectral data, and conducted field campaigns to harvest foliage samples for trait quantification. In terms of methodology, I used a suite of vegetation indices (VIs) and machine learning algorithms (MLAs) to estimate crop traits. My findings provided evidence that relatively simple VIs, as opposed to complex MLAs, can be reliably used for estimating crop traits and yield. This is an important finding in the context of crop monitoring as developing MLAs requires multiple extensive in-situ data collection campaigns. Further, results showed that UAS data with coarse spectral resolution had similar performance at estimating crop traits when compared to our spectroradiometer data with fine spectral resolution. In addition, UAS data with pixel sizes ranging from 1 cm to 1 m had similar performance in terms of correlation coefficient (r) and root mean square (RMSE) at estimating N content, suggesting that data with spatial resolution of approximately 1 m might be sufficient for monitoring crop traits. Overall, these findings can potentially aid breeders through providing rapid and non-destructive proxies of crop phenotypic traits. Moreover, my findings indicate the possibility of developing cheaper spectral monitoring instruments without sacrificing prediction accuracy of crop traits.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Remote sensing. $3 557272
650 4 $a Agriculture. $3 660421
650 4 $a Geographic information science. $3 1372545
653 $a Machine learning algorithm
653 $a Nitrogen content
653 $a Phenotyping
653 $a Spatial and spectral scale
653 $a Unmanned/Unoccupied aerial system
653 $a Winter wheat sorghum corn
655 7 $a Electronic books. $2 local $3 554714
690 $a 0799
690 $a 0370
690 $a 0473
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Oklahoma State University. $b Geography. $3 1469988
773 0 $t Dissertations Abstracts International $g 85-07B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30568885 $z click for full text (PQDT)