Predicting biomass and grain protein content using Bayesian methods

Majdi Mansouri, Marie France Destain

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper deals with the problem of predicting biomass and grain protein content using improved particle filtering (IPF) based on minimizing the Kullback–Leibler divergence. The performances of IPF are compared with those of the conventional particle filtering (PF) in two comparative studies. In the first one, we apply IPF and PF at a simple dynamic crop model with the aim to predict a single state variable, namely the winter wheat biomass, and to estimate several model parameters. In the second study, the proposed IPF and the PF are applied to a complex crop model (AZODYN) to predict a winter-wheat quality criterion, namely the grain protein content. The results of both comparative studies reveal that the IPF method provides a better estimation accuracy than the PF method. The benefit of the IPF method lies in its ability to provide accuracy related advantages over the PF method since, unlike the PF which depends on the choice of the sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of this sampling distribution, which also utilizes the observed data. The performance of the proposed method is evaluated in terms of estimation accuracy, root mean square error, mean absolute error and execution times.

Original languageEnglish
Pages (from-to)1167-1177
Number of pages11
JournalStochastic Environmental Research and Risk Assessment
Volume29
Issue number4
DOIs
Publication statusPublished - 1 May 2015
Externally publishedYes

Fingerprint

Biomass
Proteins
Crops
protein
biomass
Sampling
Mean square error
particle
method
comparative study
wheat
crop
winter
sampling
divergence

Keywords

  • Crop model
  • Particle filter
  • Prediction

ASJC Scopus subject areas

  • Environmental Engineering
  • Environmental Chemistry
  • Water Science and Technology
  • Safety, Risk, Reliability and Quality
  • Environmental Science(all)

Cite this

Predicting biomass and grain protein content using Bayesian methods. / Mansouri, Majdi; Destain, Marie France.

In: Stochastic Environmental Research and Risk Assessment, Vol. 29, No. 4, 01.05.2015, p. 1167-1177.

Research output: Contribution to journalArticle

@article{7a6f5a4b4b2d4e0c87e48af5edd7e1a3,
title = "Predicting biomass and grain protein content using Bayesian methods",
abstract = "This paper deals with the problem of predicting biomass and grain protein content using improved particle filtering (IPF) based on minimizing the Kullback–Leibler divergence. The performances of IPF are compared with those of the conventional particle filtering (PF) in two comparative studies. In the first one, we apply IPF and PF at a simple dynamic crop model with the aim to predict a single state variable, namely the winter wheat biomass, and to estimate several model parameters. In the second study, the proposed IPF and the PF are applied to a complex crop model (AZODYN) to predict a winter-wheat quality criterion, namely the grain protein content. The results of both comparative studies reveal that the IPF method provides a better estimation accuracy than the PF method. The benefit of the IPF method lies in its ability to provide accuracy related advantages over the PF method since, unlike the PF which depends on the choice of the sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of this sampling distribution, which also utilizes the observed data. The performance of the proposed method is evaluated in terms of estimation accuracy, root mean square error, mean absolute error and execution times.",
keywords = "Crop model, Particle filter, Prediction",
author = "Majdi Mansouri and Destain, {Marie France}",
year = "2015",
month = "5",
day = "1",
doi = "10.1007/s00477-015-1038-0",
language = "English",
volume = "29",
pages = "1167--1177",
journal = "Stochastic Environmental Research and Risk Assessment",
issn = "1436-3240",
publisher = "Springer New York",
number = "4",

}

TY - JOUR

T1 - Predicting biomass and grain protein content using Bayesian methods

AU - Mansouri, Majdi

AU - Destain, Marie France

PY - 2015/5/1

Y1 - 2015/5/1

N2 - This paper deals with the problem of predicting biomass and grain protein content using improved particle filtering (IPF) based on minimizing the Kullback–Leibler divergence. The performances of IPF are compared with those of the conventional particle filtering (PF) in two comparative studies. In the first one, we apply IPF and PF at a simple dynamic crop model with the aim to predict a single state variable, namely the winter wheat biomass, and to estimate several model parameters. In the second study, the proposed IPF and the PF are applied to a complex crop model (AZODYN) to predict a winter-wheat quality criterion, namely the grain protein content. The results of both comparative studies reveal that the IPF method provides a better estimation accuracy than the PF method. The benefit of the IPF method lies in its ability to provide accuracy related advantages over the PF method since, unlike the PF which depends on the choice of the sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of this sampling distribution, which also utilizes the observed data. The performance of the proposed method is evaluated in terms of estimation accuracy, root mean square error, mean absolute error and execution times.

AB - This paper deals with the problem of predicting biomass and grain protein content using improved particle filtering (IPF) based on minimizing the Kullback–Leibler divergence. The performances of IPF are compared with those of the conventional particle filtering (PF) in two comparative studies. In the first one, we apply IPF and PF at a simple dynamic crop model with the aim to predict a single state variable, namely the winter wheat biomass, and to estimate several model parameters. In the second study, the proposed IPF and the PF are applied to a complex crop model (AZODYN) to predict a winter-wheat quality criterion, namely the grain protein content. The results of both comparative studies reveal that the IPF method provides a better estimation accuracy than the PF method. The benefit of the IPF method lies in its ability to provide accuracy related advantages over the PF method since, unlike the PF which depends on the choice of the sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of this sampling distribution, which also utilizes the observed data. The performance of the proposed method is evaluated in terms of estimation accuracy, root mean square error, mean absolute error and execution times.

KW - Crop model

KW - Particle filter

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=84939944967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939944967&partnerID=8YFLogxK

U2 - 10.1007/s00477-015-1038-0

DO - 10.1007/s00477-015-1038-0

M3 - Article

AN - SCOPUS:84939944967

VL - 29

SP - 1167

EP - 1177

JO - Stochastic Environmental Research and Risk Assessment

JF - Stochastic Environmental Research and Risk Assessment

SN - 1436-3240

IS - 4

ER -