The use of reflectance data for in-season soybean yield prediction

Spyridon Mourtzinis, Scott C. Rowntree, Justin J. Suhre, Nicholas H. Weidenbenner, Eric W. Wilson, Vince M. Davis, Seth L. Naeve, Shaun N. Casteel, Brian W. Diers, Paul Esker, James E. Specht, Shawn P. Conley

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Estimation of soybean [Glycine max (L.) Merr.] yield early in the growing season is an appealing idea for both, farmers and soybean-related industries. Prior attempts to predict soybean yield have had limited success, especially when using information early in the growing season. The objective of this study was to evaluate the release date and maturity group (MG) of the cultivar, digital imaging, reflectance, and weather data during successive stages of crop development as explanatory variables in a soybean yield prediction model. The data were collected in the North Central (NC) United States at Arlington, WI (2010-2011), and Lafayette, IN (2011), using 59 MG II cultivars (released 1928-2008) at Wisconsin, and 57 MG III cultivars (released 1923-2007) at Indiana that were planted in performance trials on two planting dates (May and June). A second order polynomial regression analysis followed by ridge regression was used to develop the soybean yield prediction equation. The model accounted for 80% of the yield variability in the NC U.S. data set. An additional dataset not used in the calibration was used to conduct a validation test of the predictive performance of the model. The average difference between the fitted and actual yields in the validation test was 67 kg ha-1. Results from this study suggest that the use of cultivar release year, planting date, MG, near-infrared (NIR), visible red (RED), and Red-edge wavelength bands recorded at 77 d after planting, and weather data 30 d before and after the planting date can closely estimate soybean yields in the Midwest.

Original languageEnglish (US)
Pages (from-to)1159-1168
Number of pages10
JournalAgronomy Journal
Volume106
Issue number4
DOIs
StatePublished - Jan 1 2014

Fingerprint

reflectance
maturity groups
soybeans
prediction
planting date
cultivars
meteorological data
growing season
Midwestern United States
wavelengths
Glycine max
calibration
regression analysis
testing
image analysis
planting
farmers
industry
crops

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science

Cite this

Mourtzinis, S., Rowntree, S. C., Suhre, J. J., Weidenbenner, N. H., Wilson, E. W., Davis, V. M., ... Conley, S. P. (2014). The use of reflectance data for in-season soybean yield prediction. Agronomy Journal, 106(4), 1159-1168. https://doi.org/10.2134/agronj13.0577
Mourtzinis, Spyridon ; Rowntree, Scott C. ; Suhre, Justin J. ; Weidenbenner, Nicholas H. ; Wilson, Eric W. ; Davis, Vince M. ; Naeve, Seth L. ; Casteel, Shaun N. ; Diers, Brian W. ; Esker, Paul ; Specht, James E. ; Conley, Shawn P. / The use of reflectance data for in-season soybean yield prediction. In: Agronomy Journal. 2014 ; Vol. 106, No. 4. pp. 1159-1168.
@article{7a46100a1e3d45a4a67e29f6dba913c5,
title = "The use of reflectance data for in-season soybean yield prediction",
abstract = "Estimation of soybean [Glycine max (L.) Merr.] yield early in the growing season is an appealing idea for both, farmers and soybean-related industries. Prior attempts to predict soybean yield have had limited success, especially when using information early in the growing season. The objective of this study was to evaluate the release date and maturity group (MG) of the cultivar, digital imaging, reflectance, and weather data during successive stages of crop development as explanatory variables in a soybean yield prediction model. The data were collected in the North Central (NC) United States at Arlington, WI (2010-2011), and Lafayette, IN (2011), using 59 MG II cultivars (released 1928-2008) at Wisconsin, and 57 MG III cultivars (released 1923-2007) at Indiana that were planted in performance trials on two planting dates (May and June). A second order polynomial regression analysis followed by ridge regression was used to develop the soybean yield prediction equation. The model accounted for 80{\%} of the yield variability in the NC U.S. data set. An additional dataset not used in the calibration was used to conduct a validation test of the predictive performance of the model. The average difference between the fitted and actual yields in the validation test was 67 kg ha-1. Results from this study suggest that the use of cultivar release year, planting date, MG, near-infrared (NIR), visible red (RED), and Red-edge wavelength bands recorded at 77 d after planting, and weather data 30 d before and after the planting date can closely estimate soybean yields in the Midwest.",
author = "Spyridon Mourtzinis and Rowntree, {Scott C.} and Suhre, {Justin J.} and Weidenbenner, {Nicholas H.} and Wilson, {Eric W.} and Davis, {Vince M.} and Naeve, {Seth L.} and Casteel, {Shaun N.} and Diers, {Brian W.} and Paul Esker and Specht, {James E.} and Conley, {Shawn P.}",
year = "2014",
month = "1",
day = "1",
doi = "10.2134/agronj13.0577",
language = "English (US)",
volume = "106",
pages = "1159--1168",
journal = "Agronomy Journal",
issn = "0002-1962",
publisher = "American Society of Agronomy",
number = "4",

}

Mourtzinis, S, Rowntree, SC, Suhre, JJ, Weidenbenner, NH, Wilson, EW, Davis, VM, Naeve, SL, Casteel, SN, Diers, BW, Esker, P, Specht, JE & Conley, SP 2014, 'The use of reflectance data for in-season soybean yield prediction', Agronomy Journal, vol. 106, no. 4, pp. 1159-1168. https://doi.org/10.2134/agronj13.0577

The use of reflectance data for in-season soybean yield prediction. / Mourtzinis, Spyridon; Rowntree, Scott C.; Suhre, Justin J.; Weidenbenner, Nicholas H.; Wilson, Eric W.; Davis, Vince M.; Naeve, Seth L.; Casteel, Shaun N.; Diers, Brian W.; Esker, Paul; Specht, James E.; Conley, Shawn P.

In: Agronomy Journal, Vol. 106, No. 4, 01.01.2014, p. 1159-1168.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The use of reflectance data for in-season soybean yield prediction

AU - Mourtzinis, Spyridon

AU - Rowntree, Scott C.

AU - Suhre, Justin J.

AU - Weidenbenner, Nicholas H.

AU - Wilson, Eric W.

AU - Davis, Vince M.

AU - Naeve, Seth L.

AU - Casteel, Shaun N.

AU - Diers, Brian W.

AU - Esker, Paul

AU - Specht, James E.

AU - Conley, Shawn P.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Estimation of soybean [Glycine max (L.) Merr.] yield early in the growing season is an appealing idea for both, farmers and soybean-related industries. Prior attempts to predict soybean yield have had limited success, especially when using information early in the growing season. The objective of this study was to evaluate the release date and maturity group (MG) of the cultivar, digital imaging, reflectance, and weather data during successive stages of crop development as explanatory variables in a soybean yield prediction model. The data were collected in the North Central (NC) United States at Arlington, WI (2010-2011), and Lafayette, IN (2011), using 59 MG II cultivars (released 1928-2008) at Wisconsin, and 57 MG III cultivars (released 1923-2007) at Indiana that were planted in performance trials on two planting dates (May and June). A second order polynomial regression analysis followed by ridge regression was used to develop the soybean yield prediction equation. The model accounted for 80% of the yield variability in the NC U.S. data set. An additional dataset not used in the calibration was used to conduct a validation test of the predictive performance of the model. The average difference between the fitted and actual yields in the validation test was 67 kg ha-1. Results from this study suggest that the use of cultivar release year, planting date, MG, near-infrared (NIR), visible red (RED), and Red-edge wavelength bands recorded at 77 d after planting, and weather data 30 d before and after the planting date can closely estimate soybean yields in the Midwest.

AB - Estimation of soybean [Glycine max (L.) Merr.] yield early in the growing season is an appealing idea for both, farmers and soybean-related industries. Prior attempts to predict soybean yield have had limited success, especially when using information early in the growing season. The objective of this study was to evaluate the release date and maturity group (MG) of the cultivar, digital imaging, reflectance, and weather data during successive stages of crop development as explanatory variables in a soybean yield prediction model. The data were collected in the North Central (NC) United States at Arlington, WI (2010-2011), and Lafayette, IN (2011), using 59 MG II cultivars (released 1928-2008) at Wisconsin, and 57 MG III cultivars (released 1923-2007) at Indiana that were planted in performance trials on two planting dates (May and June). A second order polynomial regression analysis followed by ridge regression was used to develop the soybean yield prediction equation. The model accounted for 80% of the yield variability in the NC U.S. data set. An additional dataset not used in the calibration was used to conduct a validation test of the predictive performance of the model. The average difference between the fitted and actual yields in the validation test was 67 kg ha-1. Results from this study suggest that the use of cultivar release year, planting date, MG, near-infrared (NIR), visible red (RED), and Red-edge wavelength bands recorded at 77 d after planting, and weather data 30 d before and after the planting date can closely estimate soybean yields in the Midwest.

UR - http://www.scopus.com/inward/record.url?scp=84903123482&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903123482&partnerID=8YFLogxK

U2 - 10.2134/agronj13.0577

DO - 10.2134/agronj13.0577

M3 - Article

AN - SCOPUS:84903123482

VL - 106

SP - 1159

EP - 1168

JO - Agronomy Journal

JF - Agronomy Journal

SN - 0002-1962

IS - 4

ER -

Mourtzinis S, Rowntree SC, Suhre JJ, Weidenbenner NH, Wilson EW, Davis VM et al. The use of reflectance data for in-season soybean yield prediction. Agronomy Journal. 2014 Jan 1;106(4):1159-1168. https://doi.org/10.2134/agronj13.0577