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.
Similar content being viewed by others
References
Andrews B, Yi T, Iglesias P (2006) Optimal noise filtering in the chemotactic response of Escherichia coli. PLoS Comput Biol 2(11):e154
Arulampalam M, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174–188
Basso B, Ritchie J (2005) Impact of compost, manure and inorganic fertilizer on nitrate leaching and yield for a 6-year maize-alfalfa rotation in michigan. Agric Ecosyst Environ 108(4):329–341
Brisson N, Mary B, Ripoche D, Jeuffroy M, Ruget F, Nicoullaud B, Gate P, Devienne-Barret F, Antonioletti R, Durr C et al (1998) Stics: a generic model for the simulation of crops and their water and nitrogen balances. I. Theory, and parameterization applied to wheat and corn. Agronomie 18(5–6):311–346
Diepen C, Wolf J, Keulen H, Rappoldt C (1989) Wofost: a simulation model of crop production. Soil Use Manag 5(1):16–24
Elsheikh AH, Pain C, Fang F, Gomes J, Navon I (2013) Parameter estimation of subsurface flow models using iterative regularized ensemble kalman filter. Stoch Environ Res Risk Assess 27(4):877–897
Evensen G (2003) The ensemble Kalman filter: theoretical formulation and practical implementation. Ocean Dyn 53(4):343–367
Frutos E, Galindo MP, Leiva V (2014) An interactive biplot implementation in R for modeling genotype-by-environment interaction. Stoch Environ Res Risk Assess 28(1):1629–1641
Gustafsson F, Gunnarsson F, Bergman N, Forssell U, Jansson J, Karlsson R, Nordlund P (2002) Particle filters for positioning, navigation, and tracking. IEEE Trans Signal Process 50(2):425–437
Hansen S, Jensen H, Nielsen N, Svendsen H (1990) NPo-research, A10: DAISY: soil plant atmosphere system model. Miljøstyrelsen, Copenhagen
Jeuffroy M-H, Recous S (1999) Azodyn: a simple model simulating the date of nitrogen deficiency for decision support in wheat fertilization. Eur J Agron 10(2):129–144
Kandepu R, Foss B, Imsland L (2008) Applying the unscented Kalman filter for nonlinear state estimation. J Process Control 18(7):753–768
Kotecha J, Djuric P (2003) Gaussian particle filtering. IEEE Trans Signal Process 51(10):2592–2601
Lee JH, Ricker NL (1994) Extended Kalman filter based nonlinear model predictive control. Ind Eng Chem Res 33(6):1530–1541
Leisenring M, Moradkhani H (2011) Snow water equivalent prediction using bayesian data assimilation methods. Stoch Environ Res Risk Assess 25(2):253–270
Liu X, Cardiff MA, Kitanidis PK (2010) Parameter estimation in nonlinear environmental problems. Stoch Environ Res Risk Assess 24(7):1003–1022
Liu J, Chen R (1998) Sequential Monte Carlo methods for dynamic systems. J Am Stat Assoc 93(443):1032–1044
Makowski D, Jeuffroy M, Guérif M (2004) Bayesian methods for updating crop-model predictions, applications for predicting biomass and grain protein content. Frontis 3:57–68
Mansouri M, Dumont B, Destain M-F (2014) Modeling and prediction of time-varying environmental data using advanced bayesian methods. Explor Innov Success Appl Soft Comput 25(7):112–137
Mansouri M, Dumont B, Leemans V, Destain M-F (2014) Bayesian methods for predicting LAI and soil water content. Precis Agric 15(2):184–201
Matthies L, Kanade T, Szeliski R (1989) Kalman filter-based algorithms for estimating depth from image sequences. Int J Comput Vis 3(3):209–238
Meynard J-M, Cerf M, Guichard L, Jeuffroy M-H, Makowski D et al (2002) Which decision support tools for the environmental management of nitrogen? Agronomie-Sciences des Productions Vegetales et de l’Environnement 22(7–8):817–830
Sarkka S (2007) On unscented Kalman filtering for state estimation of continuous-time nonlinear systems. IEEE Trans Autom Control 52(9):1631–1641
Shu Q, Kemblowski MW, McKee M (2005) An application of ensemble Kalman filter in integral-balance subsurface modeling. Stoch Environ Res Risk Assess 19(5):361–374
Varlet-Grancher C, Bonhomme R, Chartier M, Artis P (1982) Efficience de la conversion de l’énergie solaire par un couvert végétal. Acta Oecol. Oecol Plant 3(1):3–26
Williams J, Jones C, Kiniry J, Spanel D (1989) The epic crop growth model. Trans Am Soc Agric Eng 32(2):497–511
Yan W, Hunt L, Sheng Q, Szlavnics Z (2000) Cultivar evaluation and mega-environment investigation based on the gge biplot. Crop Sci 40(3):597–605
Yang N, Tian W, Jin Z, Zhang C (2005) Particle filter for sensor fusion in a land vehicle navigation system. Meas Sci Technol 16(3):677
Acknowledgments
This work was made possible by Fonds de la Recherche Scientifique (FNRS) Grant. The statements made herein are solely the responsibility of the authors. The authors would like to thank the editor and the reviewers for the valuable comments and suggestions that enhanced the presentation and clarity of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mansouri, M., Destain, MF. Predicting biomass and grain protein content using Bayesian methods. Stoch Environ Res Risk Assess 29, 1167–1177 (2015). https://doi.org/10.1007/s00477-015-1038-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-015-1038-0