Skip to main content

Sharing, integration, and exploitation of precision livestock data

This use case is managed by the Universitat de Lleida (UdL) in cooperation with the experimental pig farm Centre of Swine Studies of Catalonia (CEP). CEP's role is primarily as a data originator, willing to share the information generated as a result of different experiments carried out on the pig farm through the data space. For CEP, it is crucial that they can maintain control over the data they provide, especially when it is generated by third parties, such as manufacturers of automatic feeding machines testing their products on the experimental farm.

Exafan precision feeding machines on a pig farm.

Some examples of use case datasets available through AgrospAI are:

Data is made available in its original format and schema, generally in a customized tabular form, following a "Pay-per-use" approach, as detailed in the good practices document Interoperability of Agri-food Data Spaces. Instead of requiring publishers to integrate data based on existing schemas, which causes significant initial overhead, this favors an incremental approach. This way, entry barriers are reduced, and data exchange is facilitated.

Later, when data integration is required, AgrospAI offers data mapping and integration services. Furthermore, data sovereignty is guaranteed by design through the "Data Room" approach. Mapped data does not leave the room; it is processed and then stored in a Knowledge Graph that remains within the room. This way, it remains under the control of the data originator, CEP. An example of a data mapping service that implements the RDF Mapping Language (RML), capable of mapping from CSV, TSV, XML, and JSON data sources to RDF-based Knowledge Graphs, is the following:

Later, CEP may decide to grant access to trusted algorithms to visit the Data Room and query the Knowledge Graph to extract the semantically integrated data relevant for their computations. Also, in this case, data sovereignty is guaranteed since only the computation results, such as aggregations or AI-trained models, can leave the room, not the original data or subsets thereof. Examples of AI services available through the AgrospAI portal include: