Machine Learning for Predicting Mycotoxin Occurrence in Maize

Abstract

Meteorological conditions are the main driving variables for mycotoxin-producing fungi and the resulting contamination in maize grain, but the cropping system used can mitigate this weather impact considerably. Several researchers have investigated cropping operations’ role in mycotoxin contamination, but these findings were inconclusive, precluding their use in predictive modeling. In this study a machine learning (ML) approach was considered, which included weather-based mechanistic model predictions for AFLA-maize and FER-maize [predicting aflatoxin B1 (AFB1) and fumonisins (FBs), respectively], and cropping system factors as the input variables. The occurrence of AFB1 and FBs in maize fields was recorded, and their corresponding cropping system data collected, over the years 2005–2018 in northern Italy. Two deep neural network (DNN) models were trained to predict, at harvest, which maize fields were contaminated beyond the legal limit with AFB1 and FBs. Both models reached an accuracy >75% demonstrating the ML approach added value with respect to classical statistical approaches (i.e., simple or multiple linear regression models). The improved predictive performance compared with that obtained for AFLA-maize and FER-maize was clearly demonstrated. This coupled to the large data set used, comprising a 13-year time series, and the good results for the statistical scores applied, together confirmed the robustness of the models developed here.

Changing climate, shifting mycotoxins: A comprehensive review of climate change impact on mycotoxin contamination

“…Lastly, more data is required to enable a better understanding of fungal and plant ecophysiology and pathogen/host interactions, especially in cropping systems, to develop and validate predictive models (Leggieri et al., 2021; Magan & Medina, 2016).…”

Comparative Analysis of Machine Learning Methods to Predict Growth of F. sporotrichioides and Production of T-2 and HT-2 Toxins in Treatments with Ethylene-Vinyl Alcohol Films Containing Pure Components of Essential Oils

“…However, in the field of application of ML in predictive mycology and prediction of mycotoxin accumulation in food or feed the number of published papers is quite low [ 39 , 47 , 48 , 49 , 50 , 53 ]. Two deep NN models were trained to predict, at harvest, which maize fields were contaminated beyond the legal limit with aflatoxin B1 and fumonisins reaching an accuracy >75% demonstrating the ML approach added value with respect to classical statistical approaches such as simple regression or MLR models [ 72 ]. A comparative study of NN, RF, and XGBoost models to predict the growth of F. culmorum and F. proliferatum and production of zearalenone and fumonisins in treatments with different formulations of three chemical fungicides at two temperatures and two a w -values in maize extract medium was carried out by our group.…”

Nutritional impact of mycotoxins in food animal production and strategies for mitigation

“…These predictive models usually use an empirical or mechanistic approach to quantify mycotoxins, and some of them have been implemented in agricultural sectors across Europe to support food source decision making for farmers [ 156 ]. Recently, a machine learning approach has been incorporated to build mycotoxin prediction models [ 156 , 157 ], which could be a promising contribution to mycotoxin control.…”