A neural network model for prediction of deoxynivalenol content in wheat grain based on weather data and preceding crop

Abstract

Deoxynivalenol (DON) is the most prevalent Fusarium toxin in Czech wheat samples and therefore forecasting this mycotoxin is a potentially useful tool to prevent it from entering into food chain. The data about DON content in wheat grain, weather conditions during the growing season and cultivation practices from two field experiments conducted in 2002–2005 were used for the development of neural network model designed for DON content prediction. The winning neural network is based on five input variables: a categorial variable – preceding crop, and continuous variables – average April temperature, sum of April precipitation, average temperature 5 days prior to anthesis, sum of precipitation 5 days prior to anthesis. The most important input parameters are the preceding crop and sum of precipitation 5 days prior to anthesis. The weather conditions in April, which are important for inoculum formation on crop debris are also of important contribution to the model. The weather conditions during May and 5 days after anthesis play only an insignificant role for the DON content in grain. The effect of soil cultivation was found inferior for model function as well. The correlation between observed and predicted data using the neural network model reached the coefficient <i>R</i><sup>2</sup> = 0.87.

DON content in oat grains in Norway related to weather conditions at different growth stages

“…A similar negative association between DON content in harvested grain and high air temperatures for the five days after flowering has been reported in wheat (Klem et al 2007). During periods with high air temperatures and limited precipitation, the water capacity of the air likely increases, resulting in lower moisture availability, which reduces the ability for the fungus to sporulate, disperse and infect oat plants.…”

“…We detected increased DON accumulation in oat grains from fields with dry and moderate to warm weather during the early phenological phases, which may be the result of better survival of F. graminearum on residues in these conditions. Similar associations between DON accumulation and warm weather during early phenological growth stages have been recorded in wheat (Klem et al 2007;Landschoot et al 2012b).…”

“…DON accumulation was enhanced in oat grains from fields with wet/moist weather around flowering and from fields with wet/moist weather in combination with high air temperatures around flowering, which correspond to the general consensus of the weather conditions that promote DON accumulation in wheat (Hooker et al 2002;Klem et al 2007;Landschoot et al 2012b).…”

“…The relationship between weather variables, especially during flowering and grain maturation, and accumulation of DON is widely documented in wheat (Hooker et al 2002;Klem et al 2007;Franz et al 2009;Landschoot et al 2012b;Andersen et al 2015). For oat, the relationship is not well explored, except for the study by Lindblad et al (2011), who stated that very little of the variation in DON could be explained by weather conditions.…”

“…The mycotoxin content in grain at harvest is variable and depends largely on the interaction of plant growth stage and weather (Hooker et al 2002;Culler et al 2007;Klem et al 2007;Cowger et al 2009;Franz et al 2009;Gourdain et al 2011;Landschoot et al 2012b;Xu et al 2013Xu et al , 2014. Weather summarisations are therefore frequently calculated within different temporal time intervals (Coakley et al 1982), fixed for the number of days (7 days, 10 days etc.…”