Predicting Mycotoxin Contamination in Irish Oats Using Deep and Transfer Learning

TL;DR

This study explores neural network and transfer learning models to accurately predict mycotoxin contamination in Irish oats, highlighting the effectiveness of transfer learning and key environmental predictors for early intervention.

Contribution

It introduces the application of transfer learning models like TabPFN, TabNet, and FT-Transformer for mycotoxin prediction in oats, demonstrating improved performance over baseline models.

Findings

TabPFN achieved the best predictive performance.

Weather history and seed moisture are key predictors.

Transfer learning models outperform traditional neural networks.

Abstract

Mycotoxin contamination poses a significant risk to cereal crop quality, food safety, and agricultural productivity. Accurate prediction of mycotoxin levels can support early intervention strategies and reduce economic losses. This study investigates the use of neural networks and transfer learning models to predict mycotoxin contamination in Irish oat crops as a multi-response prediction task. Our dataset comprises oat samples collected in Ireland, containing a mix of environmental, agronomic, and geographical predictors. Five modelling approaches were evaluated: a baseline multilayer perceptron (MLP), an MLP with pre-training, and three transfer learning models; TabPFN, TabNet, and FT-Transformer. Model performance was evaluated using regression (RMSE, $R^2$) and classification (AUC, F1) metrics, with results reported per toxin and on average. Additionally, permutation-based variable importance analysis was conducted to identify the most influential predictors across both prediction tasks. The transfer learning approach TabPFN provided the overall best performance, followed by the baseline MLP. Our variable importance analysis revealed that weather history patterns in the 90-day pre-harvest period were the most important predictors, alongside seed moisture content.