Models for food safe chains

By combining data from different links in the chain, patterns can be recognized and deviations can be addressed more quickly. For example, we have developed several models to predict the presence of mycotoxins in various types of crops. Mycotoxins are toxic substances that can be formed by fungi on crops. Such a model can use agronomic and climate data to predict whether mycotoxins will be formed in, for example, wheat.

Risk-based monitoring
We also develop models to provide input on how we can determine where in the chain we need to monitor based on risks (risk-based monitoring). For this, we use data on sampling, analysis results, information on the origin of the products, and the occurrence of various food safety hazards. This allows us to identify the products, along with potential hazards, that pose the greatest risk to human and animal health.

Better understanding of vulnerabilities
Predictive analyses and digital simulations contribute to a better understanding of vulnerabilities in the food chain and to targeted solutions. The result: greater transparency, more efficient inspections, and improved food safety. With this knowledge, companies, regulators, and policymakers can work more effectively together towards a future in which consumers can rely on safe, fair, and sustainably produced food.