Federated data & learning in food system

• Scattered
• Sensitive
• Costly to collect
• Low-motivation for data sharing

For the workshop online we used a combination of Microsoft Teams as well as MIRO. Our plan was to walk through the same rounds of conversation as we do in the live workshops, but use the possibilities of MIRO for the presentation of the content of the cards and Teams to share and discuss thoughts about it. In our experience, however, there are two challenges that have to be taken into account:

• Getting acquainted with MIRO needs time for participants, preferably prior to the workshop;
• the conversation is more static, as in an online meeting people cannot talk at the same time or jump into the conversation when they have urgent things to say. A firm and attentive workshop leader needs to make sure that everyone gets to share thoughts, one by one. Furthermore, participants need to be instructed prior to the workshop that they can comment on things being said in the chat, or by raising their virtual hand. The workshop leader needs an assistant to keep track of the chat and raise attention to what is said there, as well as to make sure that people who raise their hand get speaking time.

There is also added value of MIRO, as MIRO allows to engage with the content of the cards provided, add comments or co-produce scenarios. These options could be explored further: perhaps it is possible to use them to engage participants in a personal reflection prior to the start of the workshop.

• A federated database system (FDBS) is a type of meta-database management system (DBMS), which transparently maps multiple autonomous database systems into a single federated database
• The constituent databases are interconnected via a computer network and may be geographically decentralized.

Federated learning enables model training across multiple decentralized devices or servers while keeping the data localized. Instead of sending raw data to a central server for training, the training process takes place on the devices themselves. It helps protect data privacy and therefore motivate data sharing.

• Widespread popularity of mobile-phones and generative AI create opportunities for federated learning
• Advanced AI algorithms, such as deep learning, enable real-time integration and analysis of data, providing timely insights into aggregated food data at different levels with very low costs
• Better data privacy, benchmark with the sector-level performance, more motivation for data sharing
• Ontology development for food system can help improve data integration and mapping, data contextualization, etc., which can further accelerate the transition of the food system digitalization towards federated data & learning

If there are possible societal issues related to the digital twin, it is possible to add a new set of cards in MIRO, which present societal issues that digital twins might raise. In this round participants are asked to choose the issue that they want to debate by means of inserting their likes. The issue that receives most likes is discussed further in Teams. This phase invites participants to reflect as citizens on the future with the digital twin.

Donec facilisis tortor ut augue lacinia, at viverra est semper. Sed sapien metus, scelerisque nec pharetra id, tempor a tortor. Pellentesque non dignissim neque. Ut porta viverra est, ut dignissim elit elementum ut. Nunc vel rhoncus nibh.

Donec bibendum nunc sit amet tortor scelerisque luctus et sit amet mauris. Suspendisse felis sem, condimentum ullamcorper est sit amet, molestie mollis nulla. Etiam lorem orci, consequat ac magna quis, facilisis vehicula neque.Donec facilisis tortor ut augue lacinia, at viverra est semper. Sed sapien metus, scelerisque nec pharetra id, tempor a tortor. Pellentesque non dignissim neque. Ut porta viverra est, ut dignissim elit elementum ut. Nunc vel rhoncus nibh, ut. Ut porta viverra est, ut dignissim elit elementum ut. Nunc vel rhoncus nibh, ut.