Application of geographically weighted regression to improve grain yield prediction from unmanned aerial system imagery

Atena Haghighattalab, Jared Crain, Suchismita Mondal, Jessica Rutkoski, Ravi Prakash Singh, Jesse Poland

Research output: Contribution to journalArticle

Abstract

Phenological data are important ratings of the in-seasongrowthof crops, though this assessment is generally limited at both spatial and temporal levels during the crop cycle for large breeding nurseries. Unmanned aerial systems (UAS) have the potential to provide high spatial and temporal resolution for phenotyping tens of thousands of small field plots without requiring substantial investments in time, cost, and labor. The objective of this research was to determine whether an accurate remote sensing-based method could be developed to estimate grain yield using aerial imagery in small-plot wheat (Triticum aestivum L.) yield evaluation trials. The UAS consisted of a modified consumer-grade camera mounted on a low-cost unmanned aerial vehicle and was deployed multiple times throughout the growing season in yield trials of advanced breeding lines with irrigated and drought-stressed environments at the International Maize and Wheat Improvement Center in Ciudad Obregon, Sonora, Mexico. We assessed data quality and evaluated the potential to predict grain yield on a plot level by examining the relationships between information derived from UAS imagery and the grain yield. Using geographically weighted (GW) models, we predicted grain yield for both environments. The relationship between measured phenotypic traits derived from imagery and grain yield was highly correlated (r = 0.74 and r = 0.46 [p < 0.001] for drought and irrigated environments, respectively). Residuals from GW models were lower and less spatially dependent than methods using principal component regression, suggesting the superiority of spatially corrected models. These results show that vegetation indices collected from high-throughput UAS imagery can be used to predict grain and for selection decisions, as well as to enhance genomic selection models.

Original languageEnglish (US)
Pages (from-to)2478-2489
Number of pages12
JournalCrop Science
Volume57
Issue number5
DOIs
StatePublished - Jan 1 2017
Externally publishedYes

Fingerprint

grain yield
prediction
drought
wheat
crops
breeding lines
marker-assisted selection
cameras
remote sensing
labor
Triticum aestivum
Mexico
growing season
phenotype
corn
breeding
methodology

ASJC Scopus subject areas

  • Agronomy and Crop Science

Cite this

Application of geographically weighted regression to improve grain yield prediction from unmanned aerial system imagery. / Haghighattalab, Atena; Crain, Jared; Mondal, Suchismita; Rutkoski, Jessica; Singh, Ravi Prakash; Poland, Jesse.

In: Crop Science, Vol. 57, No. 5, 01.01.2017, p. 2478-2489.

Research output: Contribution to journalArticle

Haghighattalab, Atena ; Crain, Jared ; Mondal, Suchismita ; Rutkoski, Jessica ; Singh, Ravi Prakash ; Poland, Jesse. / Application of geographically weighted regression to improve grain yield prediction from unmanned aerial system imagery. In: Crop Science. 2017 ; Vol. 57, No. 5. pp. 2478-2489.
@article{79d2fe029daa46a1b4a898c5cbaab970,
title = "Application of geographically weighted regression to improve grain yield prediction from unmanned aerial system imagery",
abstract = "Phenological data are important ratings of the in-seasongrowthof crops, though this assessment is generally limited at both spatial and temporal levels during the crop cycle for large breeding nurseries. Unmanned aerial systems (UAS) have the potential to provide high spatial and temporal resolution for phenotyping tens of thousands of small field plots without requiring substantial investments in time, cost, and labor. The objective of this research was to determine whether an accurate remote sensing-based method could be developed to estimate grain yield using aerial imagery in small-plot wheat (Triticum aestivum L.) yield evaluation trials. The UAS consisted of a modified consumer-grade camera mounted on a low-cost unmanned aerial vehicle and was deployed multiple times throughout the growing season in yield trials of advanced breeding lines with irrigated and drought-stressed environments at the International Maize and Wheat Improvement Center in Ciudad Obregon, Sonora, Mexico. We assessed data quality and evaluated the potential to predict grain yield on a plot level by examining the relationships between information derived from UAS imagery and the grain yield. Using geographically weighted (GW) models, we predicted grain yield for both environments. The relationship between measured phenotypic traits derived from imagery and grain yield was highly correlated (r = 0.74 and r = 0.46 [p < 0.001] for drought and irrigated environments, respectively). Residuals from GW models were lower and less spatially dependent than methods using principal component regression, suggesting the superiority of spatially corrected models. These results show that vegetation indices collected from high-throughput UAS imagery can be used to predict grain and for selection decisions, as well as to enhance genomic selection models.",
author = "Atena Haghighattalab and Jared Crain and Suchismita Mondal and Jessica Rutkoski and Singh, {Ravi Prakash} and Jesse Poland",
year = "2017",
month = "1",
day = "1",
doi = "10.2135/cropsci2016.12.1016",
language = "English (US)",
volume = "57",
pages = "2478--2489",
journal = "Crop Science",
issn = "0011-183X",
publisher = "Crop Science Society of America",
number = "5",

}

TY - JOUR

T1 - Application of geographically weighted regression to improve grain yield prediction from unmanned aerial system imagery

AU - Haghighattalab, Atena

AU - Crain, Jared

AU - Mondal, Suchismita

AU - Rutkoski, Jessica

AU - Singh, Ravi Prakash

AU - Poland, Jesse

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Phenological data are important ratings of the in-seasongrowthof crops, though this assessment is generally limited at both spatial and temporal levels during the crop cycle for large breeding nurseries. Unmanned aerial systems (UAS) have the potential to provide high spatial and temporal resolution for phenotyping tens of thousands of small field plots without requiring substantial investments in time, cost, and labor. The objective of this research was to determine whether an accurate remote sensing-based method could be developed to estimate grain yield using aerial imagery in small-plot wheat (Triticum aestivum L.) yield evaluation trials. The UAS consisted of a modified consumer-grade camera mounted on a low-cost unmanned aerial vehicle and was deployed multiple times throughout the growing season in yield trials of advanced breeding lines with irrigated and drought-stressed environments at the International Maize and Wheat Improvement Center in Ciudad Obregon, Sonora, Mexico. We assessed data quality and evaluated the potential to predict grain yield on a plot level by examining the relationships between information derived from UAS imagery and the grain yield. Using geographically weighted (GW) models, we predicted grain yield for both environments. The relationship between measured phenotypic traits derived from imagery and grain yield was highly correlated (r = 0.74 and r = 0.46 [p < 0.001] for drought and irrigated environments, respectively). Residuals from GW models were lower and less spatially dependent than methods using principal component regression, suggesting the superiority of spatially corrected models. These results show that vegetation indices collected from high-throughput UAS imagery can be used to predict grain and for selection decisions, as well as to enhance genomic selection models.

AB - Phenological data are important ratings of the in-seasongrowthof crops, though this assessment is generally limited at both spatial and temporal levels during the crop cycle for large breeding nurseries. Unmanned aerial systems (UAS) have the potential to provide high spatial and temporal resolution for phenotyping tens of thousands of small field plots without requiring substantial investments in time, cost, and labor. The objective of this research was to determine whether an accurate remote sensing-based method could be developed to estimate grain yield using aerial imagery in small-plot wheat (Triticum aestivum L.) yield evaluation trials. The UAS consisted of a modified consumer-grade camera mounted on a low-cost unmanned aerial vehicle and was deployed multiple times throughout the growing season in yield trials of advanced breeding lines with irrigated and drought-stressed environments at the International Maize and Wheat Improvement Center in Ciudad Obregon, Sonora, Mexico. We assessed data quality and evaluated the potential to predict grain yield on a plot level by examining the relationships between information derived from UAS imagery and the grain yield. Using geographically weighted (GW) models, we predicted grain yield for both environments. The relationship between measured phenotypic traits derived from imagery and grain yield was highly correlated (r = 0.74 and r = 0.46 [p < 0.001] for drought and irrigated environments, respectively). Residuals from GW models were lower and less spatially dependent than methods using principal component regression, suggesting the superiority of spatially corrected models. These results show that vegetation indices collected from high-throughput UAS imagery can be used to predict grain and for selection decisions, as well as to enhance genomic selection models.

UR - http://www.scopus.com/inward/record.url?scp=85029591076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029591076&partnerID=8YFLogxK

U2 - 10.2135/cropsci2016.12.1016

DO - 10.2135/cropsci2016.12.1016

M3 - Article

AN - SCOPUS:85029591076

VL - 57

SP - 2478

EP - 2489

JO - Crop Science

JF - Crop Science

SN - 0011-183X

IS - 5

ER -