Towards data driven science in food safety

Lezing

Towards data driven science in food safety

Food supply chains are complex and vulnerable to many factors (e.g. climate, economy and human behavior) having a direct and indirect effect on the development of food safety risks. A system approach is needed that takes all of these factors into account in its complex interactions and that makes use of the huge amount of available data. In such system approach, it is clear that big data technologies and tools such as artificial intelligence and machine learning are needed, including a safe and powerful infrastructure allowing handling of big data and ensuring interoperability.

Organisator Impulse, Wageningen Data Competence Center
Datum

ma 25 februari 2019 12:30 tot 13:30

Locatie Impulse, building number 115
Stippeneng 2
115
6708 WE Wageningen
+31 317-482828

The potential of Bayesian Networks (BNs) in system approach will be demonstrated and the impact of climate and use of agrichemicals on the safety of feed for dairy cows will be used as an example. Relevant data sources and models were transferred to the WUR High Performance Cluster (WUR-HPC) infrastructure and automatic data extraction and visualization in a dashboard was realized. Both the BN model and the RIKILT big data infrastructure on WUR-HPC will be demonstrated.

It is expected that in future, the food safety WUR-HPC infrastructure developed by RIKILT will pave the road towards the implementation of the lab to the sample approach for on-line, real-time data acquisition systems that can feed food safety models on a cloud-based e-infrastructure empowering risk assessors (industry and authorities) to perform timely intervention actions at the sample site.

Hans Marvin

Hans Marvin

Hans Marvin is a senior scientist at RIKILT Wageningen University and Research, the Netherlands. His research specialisms are (i) methods for emerging risk identification & early warning, (ii) effect of drivers (among others climate change) on food safety, (iii) Big data and application of Bayesian Networks in prediction models for food safety and food fraud, iv) safety of engineered nanoparticles including stakeholders analysis (among others consumer perception), and (v) development of decision support systems.