Reference : Bayesian methods for predicting LAI and soil moisture
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Multidisciplinary, general & others
Bayesian methods for predicting LAI and soil moisture
[en] Méthodes bayésiennes pour prédire le LAI et la teneur en eau d'un sol
Mansouri, Majdi[Université de Liège - ULg > Sciences et technologie de l'environnement > Mécanique et construction >]
Dumont, Benjamin[Université de Liège - ULg > Sciences et technologie de l'environnement > Mécanique et construction >]
Destain, Marie-France[Université de Liège - ULg > Sciences et technologie de l'environnement > Mécanique et construction >]
Proceedings of the 11th International Conference on Precision Agriculture
11th International Conference on Precision Agriculture
July 15-18, 2012
The International Society of Precision Agriculture
[en] crop model ; non linear states ; parameter estimation ; variational Bayesian filter ; LAI ; soil moisture ; STICS model
[en] The prediction errors of crop models are often important due to uncertainties in the estimates of initial values of the states, in parameters, and in equations. The measurements needed to run the model are sometimes not numerous or known with some uncertainty.
In this paper, two Bayesian filtering methods were used to update the state variable values predicted by MiniSTICS model. The chosen state variates were the LAI (Leaf Area Index) of a wheat crop (Triticum aestivum L.) and the corresponding moisture content of two soil layers (0-20 cm and 30-50 cm). These state variates were estimated simultaneously with several parameters. The assessed filtering methods were the centralized Particle Filtering (PF) and the Variational Bayesian Filtering (VF). The former is known to be sensitive to the number of particles while the latter yields an optimal choice of the sampling distribution over the state variable by minimizing the Kullback-Leibler divergence. In fact, variational calculus leads to a simple Gaussian sampling distribution whose parameters (estimated iteratively) depends on the observed data. On basis of a case study, the VF method was found more efficient than the PF method. Indeed, with the VF, the Root Mean Square Error (RMSE) of the three estimated states was smaller and the convergence of the all parameters was ensured.