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 Kullback-Leibler divergence. The performances of improved particle filtering 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. Furthermore, we investigate the effect of measurement noise (e.g., different signal-to-noise ratios) on the performances of PF and IPF. In the second study, the proposed IPF and the PF are applied to a complex crop model (AZODYN) able to predict an important winter-wheat quality criterion, namely the grain protein content.They are also used to estimate the model's parameters. The results of both comparative studies show that the IPF provides a significant improvement over the PF because, unlike the PF which depends on the choice of sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of the sampling distribution, which also accounts for the observed data. The efficiency of IPF is expressed in terms of estimation accuracy (root mean square error).

Nonlinear State and Parameter Estimation Using Iterated Sigma Point Kalman Filter: Comparative Studies

“…Dynamic state-space models [1][2][3] are useful for describing data in many different areas, such as engineering [4][5][6][7][8], biological data [9,10], chemical data [11,12], and environmental data [8,[13][14][15]. Estimation of the state and model parameters based on measurements from the observation process is an essential task when analyzing data by state-space models.…”