Bayesian methods for predicting LAI and soil water content

Majdi Mansouri, Benjamin Dumont, Vincent Leemans, Marie France Destain

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

LAI of winter wheat (Triticum aestivum L.) and soil water content of the topsoil (200 mm) and of the subsoil (500 mm) were considered as state variables of a dynamic soil-crop system. This system was assumed to progress according to a Bayesian probabilistic state space model, in which real values of LAI and soil water content were daily introduced in order to correct the model trajectory and reach better future evolution. The chosen crop model was mini STICS which can reduce the computing and execution times while ensuring the robustness of data processing and estimation. To predict simultaneously state variables and model parameters in this non-linear environment, three techniques were used: extended Kalman filtering (EKF), particle filtering (PF), and variational filtering (VF). The significantly improved performance of the VF method when compared to EKF and PF is demonstrated. The variational filter has a low computational complexity and the convergence speed of states and parameters estimation can be adjusted independently. Detailed case studies demonstrated that the root mean square error of the three estimated states (LAI and soil water content of two soil layers) was smaller and that the convergence of all considered parameters was ensured when using VF. Assimilating measurements in a crop model allows accurate prediction of LAI and soil water content at a local scale. As these biophysical properties are key parameters in the crop-plant system characterization, the system has the potential to be used in precision farming to aid farmers and decision makers in developing strategies for site-specific management of inputs, such as fertilizers and water irrigation.

Original languageEnglish
Pages (from-to)184-201
Number of pages18
JournalPrecision Agriculture
Volume15
Issue number2
DOIs
Publication statusPublished - Apr 2014
Externally publishedYes

Fingerprint

Bayes Theorem
Bayesian theory
soil water content
Soil
Water
crop models
Triticum
precision agriculture
crops
subsoil
topsoil
Space Simulation
irrigation water
trajectories
winter wheat
soil
Triticum aestivum
Decision Support Techniques
Fertilizers
fertilizers

Keywords

  • Bayes
  • Crop model
  • Data assimilation
  • Extended Kalman filtering
  • Particle filtering
  • Variational filtering

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)

Cite this

Bayesian methods for predicting LAI and soil water content. / Mansouri, Majdi; Dumont, Benjamin; Leemans, Vincent; Destain, Marie France.

In: Precision Agriculture, Vol. 15, No. 2, 04.2014, p. 184-201.

Research output: Contribution to journalArticle

Mansouri, Majdi ; Dumont, Benjamin ; Leemans, Vincent ; Destain, Marie France. / Bayesian methods for predicting LAI and soil water content. In: Precision Agriculture. 2014 ; Vol. 15, No. 2. pp. 184-201.
@article{ce08c947ff67487c8e7104d4fbb786f5,
title = "Bayesian methods for predicting LAI and soil water content",
abstract = "LAI of winter wheat (Triticum aestivum L.) and soil water content of the topsoil (200 mm) and of the subsoil (500 mm) were considered as state variables of a dynamic soil-crop system. This system was assumed to progress according to a Bayesian probabilistic state space model, in which real values of LAI and soil water content were daily introduced in order to correct the model trajectory and reach better future evolution. The chosen crop model was mini STICS which can reduce the computing and execution times while ensuring the robustness of data processing and estimation. To predict simultaneously state variables and model parameters in this non-linear environment, three techniques were used: extended Kalman filtering (EKF), particle filtering (PF), and variational filtering (VF). The significantly improved performance of the VF method when compared to EKF and PF is demonstrated. The variational filter has a low computational complexity and the convergence speed of states and parameters estimation can be adjusted independently. Detailed case studies demonstrated that the root mean square error of the three estimated states (LAI and soil water content of two soil layers) was smaller and that the convergence of all considered parameters was ensured when using VF. Assimilating measurements in a crop model allows accurate prediction of LAI and soil water content at a local scale. As these biophysical properties are key parameters in the crop-plant system characterization, the system has the potential to be used in precision farming to aid farmers and decision makers in developing strategies for site-specific management of inputs, such as fertilizers and water irrigation.",
keywords = "Bayes, Crop model, Data assimilation, Extended Kalman filtering, Particle filtering, Variational filtering",
author = "Majdi Mansouri and Benjamin Dumont and Vincent Leemans and Destain, {Marie France}",
year = "2014",
month = "4",
doi = "10.1007/s11119-013-9332-7",
language = "English",
volume = "15",
pages = "184--201",
journal = "Precision Agriculture",
issn = "1385-2256",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Bayesian methods for predicting LAI and soil water content

AU - Mansouri, Majdi

AU - Dumont, Benjamin

AU - Leemans, Vincent

AU - Destain, Marie France

PY - 2014/4

Y1 - 2014/4

N2 - LAI of winter wheat (Triticum aestivum L.) and soil water content of the topsoil (200 mm) and of the subsoil (500 mm) were considered as state variables of a dynamic soil-crop system. This system was assumed to progress according to a Bayesian probabilistic state space model, in which real values of LAI and soil water content were daily introduced in order to correct the model trajectory and reach better future evolution. The chosen crop model was mini STICS which can reduce the computing and execution times while ensuring the robustness of data processing and estimation. To predict simultaneously state variables and model parameters in this non-linear environment, three techniques were used: extended Kalman filtering (EKF), particle filtering (PF), and variational filtering (VF). The significantly improved performance of the VF method when compared to EKF and PF is demonstrated. The variational filter has a low computational complexity and the convergence speed of states and parameters estimation can be adjusted independently. Detailed case studies demonstrated that the root mean square error of the three estimated states (LAI and soil water content of two soil layers) was smaller and that the convergence of all considered parameters was ensured when using VF. Assimilating measurements in a crop model allows accurate prediction of LAI and soil water content at a local scale. As these biophysical properties are key parameters in the crop-plant system characterization, the system has the potential to be used in precision farming to aid farmers and decision makers in developing strategies for site-specific management of inputs, such as fertilizers and water irrigation.

AB - LAI of winter wheat (Triticum aestivum L.) and soil water content of the topsoil (200 mm) and of the subsoil (500 mm) were considered as state variables of a dynamic soil-crop system. This system was assumed to progress according to a Bayesian probabilistic state space model, in which real values of LAI and soil water content were daily introduced in order to correct the model trajectory and reach better future evolution. The chosen crop model was mini STICS which can reduce the computing and execution times while ensuring the robustness of data processing and estimation. To predict simultaneously state variables and model parameters in this non-linear environment, three techniques were used: extended Kalman filtering (EKF), particle filtering (PF), and variational filtering (VF). The significantly improved performance of the VF method when compared to EKF and PF is demonstrated. The variational filter has a low computational complexity and the convergence speed of states and parameters estimation can be adjusted independently. Detailed case studies demonstrated that the root mean square error of the three estimated states (LAI and soil water content of two soil layers) was smaller and that the convergence of all considered parameters was ensured when using VF. Assimilating measurements in a crop model allows accurate prediction of LAI and soil water content at a local scale. As these biophysical properties are key parameters in the crop-plant system characterization, the system has the potential to be used in precision farming to aid farmers and decision makers in developing strategies for site-specific management of inputs, such as fertilizers and water irrigation.

KW - Bayes

KW - Crop model

KW - Data assimilation

KW - Extended Kalman filtering

KW - Particle filtering

KW - Variational filtering

UR - http://www.scopus.com/inward/record.url?scp=84896853720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896853720&partnerID=8YFLogxK

U2 - 10.1007/s11119-013-9332-7

DO - 10.1007/s11119-013-9332-7

M3 - Article

VL - 15

SP - 184

EP - 201

JO - Precision Agriculture

JF - Precision Agriculture

SN - 1385-2256

IS - 2

ER -