Ordinal regression models for predicting deoxynivalenol in winter wheat
- Author
- Sofie Landschoot (UGent) , Willem Waegeman (UGent) , Kris Audenaert (UGent) , Geert Haesaert (UGent) and Bernard De Baets (UGent)
- Organization
- Abstract
- Deoxynivalenol (DON) is one of the most prevalent toxins in Fusarium-infected wheat samples. Accurate forecasting systems that predict the presence of DON are useful to underpin decision making on the application of fungicides, to identify fields under risk, and to help minimize the risk of food and feed contamination with DON. To this end, existing forecasting systems often adopt statistical regression models, in which attempts are made to predict DON values as a continuous variable. In contrast, this paper advocates the use of ordinal regression models for the prediction of DON values, by defining thresholds for converting continuous DON values into a fixed number of well-chosen risk classes. Objective criteria for selecting these thresholds in a meaningful way are proposed. The resulting approach was evaluated on a sizeable field experiment in Belgium, for which measurements of DON values and various types of predictor variables were collected at 18 locations during 2002-2011. The results demonstrate that modelling and evaluating DON values on an ordinal scale leads to a more accurate and more easily interpreted predictive performance. Compared to traditional regression models, an improvement could be observed for support vector ordinal regression models and proportional odds models.
- Keywords
- fusarium head blight, deoxynivalenol, ordinal regression, FUSARIUM HEAD BLIGHT, WEATHER DATA, VARIABLES, INFECTION, FLANDERS, BELGIUM, CROP
Downloads
-
(...).pdf
- full text
- |
- UGent only
- |
- |
- 185.64 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-4207878
- MLA
- Landschoot, Sofie, et al. “Ordinal Regression Models for Predicting Deoxynivalenol in Winter Wheat.” PLANT PATHOLOGY, vol. 62, no. 6, 2013, pp. 1319–29, doi:10.1111/ppa.12041.
- APA
- Landschoot, S., Waegeman, W., Audenaert, K., Haesaert, G., & De Baets, B. (2013). Ordinal regression models for predicting deoxynivalenol in winter wheat. PLANT PATHOLOGY, 62(6), 1319–1329. https://doi.org/10.1111/ppa.12041
- Chicago author-date
- Landschoot, Sofie, Willem Waegeman, Kris Audenaert, Geert Haesaert, and Bernard De Baets. 2013. “Ordinal Regression Models for Predicting Deoxynivalenol in Winter Wheat.” PLANT PATHOLOGY 62 (6): 1319–29. https://doi.org/10.1111/ppa.12041.
- Chicago author-date (all authors)
- Landschoot, Sofie, Willem Waegeman, Kris Audenaert, Geert Haesaert, and Bernard De Baets. 2013. “Ordinal Regression Models for Predicting Deoxynivalenol in Winter Wheat.” PLANT PATHOLOGY 62 (6): 1319–1329. doi:10.1111/ppa.12041.
- Vancouver
- 1.Landschoot S, Waegeman W, Audenaert K, Haesaert G, De Baets B. Ordinal regression models for predicting deoxynivalenol in winter wheat. PLANT PATHOLOGY. 2013;62(6):1319–29.
- IEEE
- [1]S. Landschoot, W. Waegeman, K. Audenaert, G. Haesaert, and B. De Baets, “Ordinal regression models for predicting deoxynivalenol in winter wheat,” PLANT PATHOLOGY, vol. 62, no. 6, pp. 1319–1329, 2013.
@article{4207878,
abstract = {{Deoxynivalenol (DON) is one of the most prevalent toxins in Fusarium-infected wheat samples. Accurate forecasting systems that predict the presence of DON are useful to underpin decision making on the application of fungicides, to identify fields under risk, and to help minimize the risk of food and feed contamination with DON. To this end, existing forecasting systems often adopt statistical regression models, in which attempts are made to predict DON values as a continuous variable. In contrast, this paper advocates the use of ordinal regression models for the prediction of DON values, by defining thresholds for converting continuous DON values into a fixed number of well-chosen risk classes. Objective criteria for selecting these thresholds in a meaningful way are proposed. The resulting approach was evaluated on a sizeable field experiment in Belgium, for which measurements of DON values and various types of predictor variables were collected at 18 locations during 2002-2011. The results demonstrate that modelling and evaluating DON values on an ordinal scale leads to a more accurate and more easily interpreted predictive performance. Compared to traditional regression models, an improvement could be observed for support vector ordinal regression models and proportional odds models.}},
author = {{Landschoot, Sofie and Waegeman, Willem and Audenaert, Kris and Haesaert, Geert and De Baets, Bernard}},
issn = {{0032-0862}},
journal = {{PLANT PATHOLOGY}},
keywords = {{fusarium head blight,deoxynivalenol,ordinal regression,FUSARIUM HEAD BLIGHT,WEATHER DATA,VARIABLES,INFECTION,FLANDERS,BELGIUM,CROP}},
language = {{eng}},
number = {{6}},
pages = {{1319--1329}},
title = {{Ordinal regression models for predicting deoxynivalenol in winter wheat}},
url = {{http://doi.org/10.1111/ppa.12041}},
volume = {{62}},
year = {{2013}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: