A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model

Derek Groenendyk, Kelly Thorp, Paul A Ferre, Wade Crow, Doug Hunsaker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Soil moisture, especially under drought conditions, is a factor that is known to impact crop yield predictions. Crop growth models used to make these predictions rely on soil texture estimates, which influence simulated soil moisture and ultimately crop growth. The purpose of this research was to implement a k-means clustering approach to address the uncertainty of the soil texture estimates. By grouping similar soil textures based on their simulated responses, clustering reveals how soil texture uncertainty may impact yield estimates. Wheat growth simulations were conducted using a HYDRUS 1D and coupled crop model for soils defined on the USDA soil texture triangle. A k-means clustering algorithm was applied to the simulated biophysical data for each soil texture. Resulting clusters were different from traditional soil type classifications. The k-means clustering approach proved useful for investigating the relationship to soil texture that crop yield may have. This research shows that the impact of soil texture variation should be considered when conducting crop growth simulation for the purposes of yield forecasting.

Original languageEnglish (US)
Title of host publicationProceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014
PublisherInternational Environmental Modelling and Software Society
Pages1326-1333
Number of pages8
Volume3
StatePublished - 2014
Event7th International Congress on Environmental Modelling and Software, iEMSs 2014 - San Diego, United States
Duration: Jun 15 2014Jun 19 2014

Other

Other7th International Congress on Environmental Modelling and Software, iEMSs 2014
CountryUnited States
CitySan Diego
Period6/15/146/19/14

Fingerprint

Coupled Model
K-means Clustering
Wheat
Crops
Soil
Texture
Soils
Uncertainty
Textures
Prediction
Soil Moisture
Soil moisture
Estimate
Drought
K-means Algorithm
Growth Model
Clustering algorithms
Grouping
Clustering Algorithm
Forecasting

Keywords

  • Clustering
  • HYDRUS
  • Modeling
  • Soil moisture
  • Yield

ASJC Scopus subject areas

  • Software
  • Environmental Engineering
  • Modeling and Simulation

Cite this

Groenendyk, D., Thorp, K., Ferre, P. A., Crow, W., & Hunsaker, D. (2014). A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model. In Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014 (Vol. 3, pp. 1326-1333). International Environmental Modelling and Software Society.

A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model. / Groenendyk, Derek; Thorp, Kelly; Ferre, Paul A; Crow, Wade; Hunsaker, Doug.

Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014. Vol. 3 International Environmental Modelling and Software Society, 2014. p. 1326-1333.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Groenendyk, D, Thorp, K, Ferre, PA, Crow, W & Hunsaker, D 2014, A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model. in Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014. vol. 3, International Environmental Modelling and Software Society, pp. 1326-1333, 7th International Congress on Environmental Modelling and Software, iEMSs 2014, San Diego, United States, 6/15/14.
Groenendyk D, Thorp K, Ferre PA, Crow W, Hunsaker D. A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model. In Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014. Vol. 3. International Environmental Modelling and Software Society. 2014. p. 1326-1333
Groenendyk, Derek ; Thorp, Kelly ; Ferre, Paul A ; Crow, Wade ; Hunsaker, Doug. / A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model. Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014. Vol. 3 International Environmental Modelling and Software Society, 2014. pp. 1326-1333
@inproceedings{5a4ab69dc399423bb6ceaae7ed3dbc9b,
title = "A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model",
abstract = "Soil moisture, especially under drought conditions, is a factor that is known to impact crop yield predictions. Crop growth models used to make these predictions rely on soil texture estimates, which influence simulated soil moisture and ultimately crop growth. The purpose of this research was to implement a k-means clustering approach to address the uncertainty of the soil texture estimates. By grouping similar soil textures based on their simulated responses, clustering reveals how soil texture uncertainty may impact yield estimates. Wheat growth simulations were conducted using a HYDRUS 1D and coupled crop model for soils defined on the USDA soil texture triangle. A k-means clustering algorithm was applied to the simulated biophysical data for each soil texture. Resulting clusters were different from traditional soil type classifications. The k-means clustering approach proved useful for investigating the relationship to soil texture that crop yield may have. This research shows that the impact of soil texture variation should be considered when conducting crop growth simulation for the purposes of yield forecasting.",
keywords = "Clustering, HYDRUS, Modeling, Soil moisture, Yield",
author = "Derek Groenendyk and Kelly Thorp and Ferre, {Paul A} and Wade Crow and Doug Hunsaker",
year = "2014",
language = "English (US)",
volume = "3",
pages = "1326--1333",
booktitle = "Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014",
publisher = "International Environmental Modelling and Software Society",

}

TY - GEN

T1 - A k-means clustering approach to assess wheat yield prediction uncertainty with a HYDRUS-1D coupled crop model

AU - Groenendyk, Derek

AU - Thorp, Kelly

AU - Ferre, Paul A

AU - Crow, Wade

AU - Hunsaker, Doug

PY - 2014

Y1 - 2014

N2 - Soil moisture, especially under drought conditions, is a factor that is known to impact crop yield predictions. Crop growth models used to make these predictions rely on soil texture estimates, which influence simulated soil moisture and ultimately crop growth. The purpose of this research was to implement a k-means clustering approach to address the uncertainty of the soil texture estimates. By grouping similar soil textures based on their simulated responses, clustering reveals how soil texture uncertainty may impact yield estimates. Wheat growth simulations were conducted using a HYDRUS 1D and coupled crop model for soils defined on the USDA soil texture triangle. A k-means clustering algorithm was applied to the simulated biophysical data for each soil texture. Resulting clusters were different from traditional soil type classifications. The k-means clustering approach proved useful for investigating the relationship to soil texture that crop yield may have. This research shows that the impact of soil texture variation should be considered when conducting crop growth simulation for the purposes of yield forecasting.

AB - Soil moisture, especially under drought conditions, is a factor that is known to impact crop yield predictions. Crop growth models used to make these predictions rely on soil texture estimates, which influence simulated soil moisture and ultimately crop growth. The purpose of this research was to implement a k-means clustering approach to address the uncertainty of the soil texture estimates. By grouping similar soil textures based on their simulated responses, clustering reveals how soil texture uncertainty may impact yield estimates. Wheat growth simulations were conducted using a HYDRUS 1D and coupled crop model for soils defined on the USDA soil texture triangle. A k-means clustering algorithm was applied to the simulated biophysical data for each soil texture. Resulting clusters were different from traditional soil type classifications. The k-means clustering approach proved useful for investigating the relationship to soil texture that crop yield may have. This research shows that the impact of soil texture variation should be considered when conducting crop growth simulation for the purposes of yield forecasting.

KW - Clustering

KW - HYDRUS

KW - Modeling

KW - Soil moisture

KW - Yield

UR - http://www.scopus.com/inward/record.url?scp=84911873532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911873532&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 1326

EP - 1333

BT - Proceedings - 7th International Congress on Environmental Modelling and Software: Bold Visions for Environmental Modeling, iEMSs 2014

PB - International Environmental Modelling and Software Society

ER -