Universal digital twin

A new paper proposes a dynamic knowledge graph approach for digital twins and the eventual goal of a Universal Digital Twin.

The dynamic knowledge graph draws from the Semantic Web. It is composed of ontologies, and computational agents that update the knowledge graph. It ensures that data are connected, discoverable and queryable. The knowledge graph includes a base world that describes the real world and the notion of parallel worlds which predict outcomes of transformations on the base world without altering it. The knowledge graph can host geospatial and chemical data, control chemistry experiments, perform cross-domain simulations and perform scenario analysis.

The Semantic Web provides a descriptive representation of data on the World Wide Web. These resources are ontologies which are a collection of classes, object properties and data properties expressing facts about and a semantic model of a domain of interest. 

Linked data is Semantic Web data that is linked to other Semantic Web data for exploration and discovery. Linked Data uses resource description framework (RDF) to store data in the form subject, predicate and object triples. 

A knowledge graph is a network of data expressed as a graph where the nodes of the graph are concepts of their instances (data items) and the edges of the graph are links between related concepts or instances. Knowledge graphs are often built using Linked Data principles. They provide a powerful method to host, query and traverse data and to find and retrieve related information.

https://www.cambridge.org/core/journals/data-centric-engineering/article/universal-digital-twin-a-dynamic-knowledge-graph/FD25CDFF886CD2ED33D1FDFC13F6BEAB#