agrifoodtech.cofund@upct.es
Big data and artificial intelligence for food safety
Research Code: C1-BIG DATA
| What are we looking for
We are seeking innovative research proposals that aim to contribute to advances in food safety risk assessment through open and data-driven approaches, supporting more informed decision-making across the food supply chain.
Keep in mind that supervisors are not allowed to get involved in the project proposal preparation.
The Context:
The advances in sensor and information technologies, coupled with increased computational capabilities, have resulted in a substantial growth in the volume and diversity of data available in the food sector. This includes real-time sensor data generated through Internet of Things technologies, as well as historical datasets and information from public databases. While the exploitation of such data has already enabled significant advances in other domains, such as Industry 4.0, its potential application to enhance food safety remains relatively underexplored.
The problem to address:
Despite the increasing availability of large and diverse data sources in the food sector, effectively exploiting this information to support food safety risk assessment remains a major challenge. Key difficulties include the integration of heterogeneous data, the handling of uncertainty and complexity, and the translation of analytical outputs into forms that can meaningfully support decision-making within food industry contexts.
Objectives:
Approaches for integrating information of different nature (e.g., real-time sensor data, environmental data, historical datasets, and biological knowledge) within the context of food safety, with attention to data integrity and their potential use in supporting decision-making.
Mathematical or computational models, including artificial intelligence-based approaches, that make use of such information flows and address uncertainty and complexity in relation to food safety risk assessment.
Translation of model outputs into decision-support concepts and practical pathways for uptake by food safety stakeholders.
Expected Outcomes:
Research conducted under this line may contribute to advancing understanding of how data-driven and artificial intelligence-based approaches can support food safety risk assessment and decision-making across the food supply chain. Possible outcomes may include:
- Potential advances in how heterogeneous information sources can be integrated to inform food safety decision-making.
- Contributions to improved understanding of the potential role of artificial intelligence in supporting food safety risk assessment.
- Insights into pathways relating analytical or model-based outputs to decision-support concepts relevant to food safety stakeholders.
- Contributions to improved understanding of uncertainty, complexity and robustness considerations in data-driven food safety risk assessment.
Candidate Qualifications (if any):
Candidates may come from a broad range of disciplines relevant to the topic, including food safety, microbiology, computational biology, machine learning, artificial intelligence, data science, or other related scientific fields. Familiarity with data-driven or computational approaches relevant to food safety research would be considered an asset.