Prediction of non-linear time-variant dynamic crop model using Bayesian methods

Majdi Mansouri, B. Dumont, M. F. Destain

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

2 Citations (Scopus)

Abstract

This work addresses the problem of predicting a non-linear time-variant leaf area index and soil moisture model (LSM) using state estimation. These techniques include the extended Kalman filter (EKF), particle filter (PF) and the more recently developed technique, variational filter (VF). In the comparative study, the state variables (the leaf-area index LAI, the volumetric water content of the layer 1, HUR1 and the volumetric water content of the layer 2, HUR2) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error with respect to the noise-free data. The results show that VF provides a significant improvement over EKF and PF.

Original languageEnglish
Title of host publicationPrecision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013
Pages507-513
Number of pages7
Publication statusPublished - 2013
Externally publishedYes
Event9th European Conference on Precision Agriculture, ECPA 2013 - Lleida, Catalonia, Spain
Duration: 7 Jul 201311 Jul 2013

Other

Other9th European Conference on Precision Agriculture, ECPA 2013
CountrySpain
CityLleida, Catalonia
Period7/7/1311/7/13

Fingerprint

crop models
Bayesian theory
dynamic models
leaf area index
prediction
water content
methodology
soil water

Keywords

  • Crop model
  • Extended Kalman filter
  • LAI
  • Particle filter
  • Soil moisture prediction
  • Variational filter

ASJC Scopus subject areas

  • Agronomy and Crop Science

Cite this

Mansouri, M., Dumont, B., & Destain, M. F. (2013). Prediction of non-linear time-variant dynamic crop model using Bayesian methods. In Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013 (pp. 507-513)

Prediction of non-linear time-variant dynamic crop model using Bayesian methods. / Mansouri, Majdi; Dumont, B.; Destain, M. F.

Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013. 2013. p. 507-513.

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

Mansouri, M, Dumont, B & Destain, MF 2013, Prediction of non-linear time-variant dynamic crop model using Bayesian methods. in Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013. pp. 507-513, 9th European Conference on Precision Agriculture, ECPA 2013, Lleida, Catalonia, Spain, 7/7/13.
Mansouri M, Dumont B, Destain MF. Prediction of non-linear time-variant dynamic crop model using Bayesian methods. In Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013. 2013. p. 507-513
Mansouri, Majdi ; Dumont, B. ; Destain, M. F. / Prediction of non-linear time-variant dynamic crop model using Bayesian methods. Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013. 2013. pp. 507-513
@inproceedings{47ee1633d37444959563bc660a4b6170,
title = "Prediction of non-linear time-variant dynamic crop model using Bayesian methods",
abstract = "This work addresses the problem of predicting a non-linear time-variant leaf area index and soil moisture model (LSM) using state estimation. These techniques include the extended Kalman filter (EKF), particle filter (PF) and the more recently developed technique, variational filter (VF). In the comparative study, the state variables (the leaf-area index LAI, the volumetric water content of the layer 1, HUR1 and the volumetric water content of the layer 2, HUR2) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error with respect to the noise-free data. The results show that VF provides a significant improvement over EKF and PF.",
keywords = "Crop model, Extended Kalman filter, LAI, Particle filter, Soil moisture prediction, Variational filter",
author = "Majdi Mansouri and B. Dumont and Destain, {M. F.}",
year = "2013",
language = "English",
isbn = "9789086862245",
pages = "507--513",
booktitle = "Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013",

}

TY - GEN

T1 - Prediction of non-linear time-variant dynamic crop model using Bayesian methods

AU - Mansouri, Majdi

AU - Dumont, B.

AU - Destain, M. F.

PY - 2013

Y1 - 2013

N2 - This work addresses the problem of predicting a non-linear time-variant leaf area index and soil moisture model (LSM) using state estimation. These techniques include the extended Kalman filter (EKF), particle filter (PF) and the more recently developed technique, variational filter (VF). In the comparative study, the state variables (the leaf-area index LAI, the volumetric water content of the layer 1, HUR1 and the volumetric water content of the layer 2, HUR2) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error with respect to the noise-free data. The results show that VF provides a significant improvement over EKF and PF.

AB - This work addresses the problem of predicting a non-linear time-variant leaf area index and soil moisture model (LSM) using state estimation. These techniques include the extended Kalman filter (EKF), particle filter (PF) and the more recently developed technique, variational filter (VF). In the comparative study, the state variables (the leaf-area index LAI, the volumetric water content of the layer 1, HUR1 and the volumetric water content of the layer 2, HUR2) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error with respect to the noise-free data. The results show that VF provides a significant improvement over EKF and PF.

KW - Crop model

KW - Extended Kalman filter

KW - LAI

KW - Particle filter

KW - Soil moisture prediction

KW - Variational filter

UR - http://www.scopus.com/inward/record.url?scp=84893390602&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893390602&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84893390602

SN - 9789086862245

SP - 507

EP - 513

BT - Precision Agriculture 2013 - Papers Presented at the 9th European Conference on Precision Agriculture, ECPA 2013

ER -