Latent heat and sensible heat flux simulation in maize using artificial neural networks

Babak Safa, Timothy J. Arkebauer, Qiuming Zhu, Andy Suyker, Suat Irmak

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Latent Heat (LE) and Sensible Heat (H) flux are two major components of the energy balance at the earth's surface, which play important roles in the water cycle and global warming. There are various methods for their estimation or measurement. Eddy covariance is a direct and accurate technique for their measurement. Some limitations lead to prevention of the extensive use of the eddy covariance technique. Therefore, simulation approaches can be utilized for their estimation. ANNs are the information processing systems, which can inspect the empirical data and investigate the relations (hidden rules) among them, and then make the network structure. In this study, multi-layer perceptron neural network trained by the steepest descent Back-Propagation (BP) algorithm was tested to simulate LE and H flux above two maize sites (rain-fed & irrigated) near Mead, Nebraska. Network training and testing was fulfilled using on two different subsets of the hourly data which were selected from days of year (DOY) 169 to 222 for 2001, 2003, 2005, 2007, and 2009. The results showed high correlation between actual and estimated data; the R2 values for LE flux in irrigated and rain-fed sites were 0.9576, and 0.9642; and for H flux 0.8001, and 0.8478, respectively. Furthermore, the RMSE values ranged from 0.0580 to 0.0721 W/m2 for LE flux and from 0.0824 to 0.0863 W/m2 for H flux. In addition, the sensitivity of the fluxes with respect to each input was analyzed over the growth stages so that the most powerful effects among the inputs for LE flux were identified as net radiation, leaf area index, vapor pressure deficit, and wind speed, and for H flux net radiation, wind speed, air temperature, leaf area index and vapor pressure deficit. Furthermore, to achieve the minimal set of input in order to speed up the analysis procedures, the impact intensity of each input on the fluxes was recognized by deactivation of each input vector in network training. This study reveals that artificial neural networks are not only a powerful technique for estimation of LE and H fluxes, but also can identify the effectiveness of each input on the fluxes.

Original languageEnglish (US)
Pages (from-to)155-164
Number of pages10
JournalComputers and Electronics in Agriculture
Volume154
DOIs
StatePublished - Nov 2018

Fingerprint

Latent heat
latent heat flux
sensible heat flux
artificial neural network
neural networks
Heat flux
maize
net radiation
eddy covariance
Fluxes
Neural networks
heat
vapor pressure
leaf area index
corn
wind velocity
simulation
information processing
back propagation
energy balance

Keywords

  • Artificial neural networks
  • Eddy covariance
  • Flux measurement
  • Latent heat and sensible heat exchange
  • Sensitivity analysis

ASJC Scopus subject areas

  • Forestry
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

Latent heat and sensible heat flux simulation in maize using artificial neural networks. / Safa, Babak; Arkebauer, Timothy J.; Zhu, Qiuming; Suyker, Andy; Irmak, Suat.

In: Computers and Electronics in Agriculture, Vol. 154, 11.2018, p. 155-164.

Research output: Contribution to journalArticle

Safa, Babak ; Arkebauer, Timothy J. ; Zhu, Qiuming ; Suyker, Andy ; Irmak, Suat. / Latent heat and sensible heat flux simulation in maize using artificial neural networks. In: Computers and Electronics in Agriculture. 2018 ; Vol. 154. pp. 155-164.
@article{26c941a584274d41b1fd91181abd6612,
title = "Latent heat and sensible heat flux simulation in maize using artificial neural networks",
abstract = "Latent Heat (LE) and Sensible Heat (H) flux are two major components of the energy balance at the earth's surface, which play important roles in the water cycle and global warming. There are various methods for their estimation or measurement. Eddy covariance is a direct and accurate technique for their measurement. Some limitations lead to prevention of the extensive use of the eddy covariance technique. Therefore, simulation approaches can be utilized for their estimation. ANNs are the information processing systems, which can inspect the empirical data and investigate the relations (hidden rules) among them, and then make the network structure. In this study, multi-layer perceptron neural network trained by the steepest descent Back-Propagation (BP) algorithm was tested to simulate LE and H flux above two maize sites (rain-fed & irrigated) near Mead, Nebraska. Network training and testing was fulfilled using on two different subsets of the hourly data which were selected from days of year (DOY) 169 to 222 for 2001, 2003, 2005, 2007, and 2009. The results showed high correlation between actual and estimated data; the R2 values for LE flux in irrigated and rain-fed sites were 0.9576, and 0.9642; and for H flux 0.8001, and 0.8478, respectively. Furthermore, the RMSE values ranged from 0.0580 to 0.0721 W/m2 for LE flux and from 0.0824 to 0.0863 W/m2 for H flux. In addition, the sensitivity of the fluxes with respect to each input was analyzed over the growth stages so that the most powerful effects among the inputs for LE flux were identified as net radiation, leaf area index, vapor pressure deficit, and wind speed, and for H flux net radiation, wind speed, air temperature, leaf area index and vapor pressure deficit. Furthermore, to achieve the minimal set of input in order to speed up the analysis procedures, the impact intensity of each input on the fluxes was recognized by deactivation of each input vector in network training. This study reveals that artificial neural networks are not only a powerful technique for estimation of LE and H fluxes, but also can identify the effectiveness of each input on the fluxes.",
keywords = "Artificial neural networks, Eddy covariance, Flux measurement, Latent heat and sensible heat exchange, Sensitivity analysis",
author = "Babak Safa and Arkebauer, {Timothy J.} and Qiuming Zhu and Andy Suyker and Suat Irmak",
year = "2018",
month = "11",
doi = "10.1016/j.compag.2018.08.038",
language = "English (US)",
volume = "154",
pages = "155--164",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

TY - JOUR

T1 - Latent heat and sensible heat flux simulation in maize using artificial neural networks

AU - Safa, Babak

AU - Arkebauer, Timothy J.

AU - Zhu, Qiuming

AU - Suyker, Andy

AU - Irmak, Suat

PY - 2018/11

Y1 - 2018/11

N2 - Latent Heat (LE) and Sensible Heat (H) flux are two major components of the energy balance at the earth's surface, which play important roles in the water cycle and global warming. There are various methods for their estimation or measurement. Eddy covariance is a direct and accurate technique for their measurement. Some limitations lead to prevention of the extensive use of the eddy covariance technique. Therefore, simulation approaches can be utilized for their estimation. ANNs are the information processing systems, which can inspect the empirical data and investigate the relations (hidden rules) among them, and then make the network structure. In this study, multi-layer perceptron neural network trained by the steepest descent Back-Propagation (BP) algorithm was tested to simulate LE and H flux above two maize sites (rain-fed & irrigated) near Mead, Nebraska. Network training and testing was fulfilled using on two different subsets of the hourly data which were selected from days of year (DOY) 169 to 222 for 2001, 2003, 2005, 2007, and 2009. The results showed high correlation between actual and estimated data; the R2 values for LE flux in irrigated and rain-fed sites were 0.9576, and 0.9642; and for H flux 0.8001, and 0.8478, respectively. Furthermore, the RMSE values ranged from 0.0580 to 0.0721 W/m2 for LE flux and from 0.0824 to 0.0863 W/m2 for H flux. In addition, the sensitivity of the fluxes with respect to each input was analyzed over the growth stages so that the most powerful effects among the inputs for LE flux were identified as net radiation, leaf area index, vapor pressure deficit, and wind speed, and for H flux net radiation, wind speed, air temperature, leaf area index and vapor pressure deficit. Furthermore, to achieve the minimal set of input in order to speed up the analysis procedures, the impact intensity of each input on the fluxes was recognized by deactivation of each input vector in network training. This study reveals that artificial neural networks are not only a powerful technique for estimation of LE and H fluxes, but also can identify the effectiveness of each input on the fluxes.

AB - Latent Heat (LE) and Sensible Heat (H) flux are two major components of the energy balance at the earth's surface, which play important roles in the water cycle and global warming. There are various methods for their estimation or measurement. Eddy covariance is a direct and accurate technique for their measurement. Some limitations lead to prevention of the extensive use of the eddy covariance technique. Therefore, simulation approaches can be utilized for their estimation. ANNs are the information processing systems, which can inspect the empirical data and investigate the relations (hidden rules) among them, and then make the network structure. In this study, multi-layer perceptron neural network trained by the steepest descent Back-Propagation (BP) algorithm was tested to simulate LE and H flux above two maize sites (rain-fed & irrigated) near Mead, Nebraska. Network training and testing was fulfilled using on two different subsets of the hourly data which were selected from days of year (DOY) 169 to 222 for 2001, 2003, 2005, 2007, and 2009. The results showed high correlation between actual and estimated data; the R2 values for LE flux in irrigated and rain-fed sites were 0.9576, and 0.9642; and for H flux 0.8001, and 0.8478, respectively. Furthermore, the RMSE values ranged from 0.0580 to 0.0721 W/m2 for LE flux and from 0.0824 to 0.0863 W/m2 for H flux. In addition, the sensitivity of the fluxes with respect to each input was analyzed over the growth stages so that the most powerful effects among the inputs for LE flux were identified as net radiation, leaf area index, vapor pressure deficit, and wind speed, and for H flux net radiation, wind speed, air temperature, leaf area index and vapor pressure deficit. Furthermore, to achieve the minimal set of input in order to speed up the analysis procedures, the impact intensity of each input on the fluxes was recognized by deactivation of each input vector in network training. This study reveals that artificial neural networks are not only a powerful technique for estimation of LE and H fluxes, but also can identify the effectiveness of each input on the fluxes.

KW - Artificial neural networks

KW - Eddy covariance

KW - Flux measurement

KW - Latent heat and sensible heat exchange

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=85053144924&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053144924&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2018.08.038

DO - 10.1016/j.compag.2018.08.038

M3 - Article

AN - SCOPUS:85053144924

VL - 154

SP - 155

EP - 164

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

ER -