Digital Twins (DTs) and big data are mutually reinforcing technologies since huge volumes of data representing the physical/virtual worlds are collected, transformed, and generated through models to aggregate value to the business. Modern DTs follow a five-component architecture, which includes a Data Management (DM) component that bridges a physical system, a mirrored virtual one, and services components. However, there is no clarity on the functionality required for the DM component. We analyze the DM component under the big data value chain activities, highlighting key issues to be addressed (e.g., data heterogeneity, interoperability, integration, search), and proposing conceptual and technological solutions for the key challenges. Our goals are:

• To define the role and the core data management functionality for a DT targeted at the Oil & Gas industry;
• To propose a reference data management architecture aligned with the Data Lakehouse concept;
• To investigate appropriate technological platforms to support the DM component, and its interconnection with the other components (physical, virtual and services);
• To investigate the particular role, contribution and limitations of the OSDU (Open Subsurface Data Universe) platform and other industry standards as an enabling technology for data management in DTs.

Data Management Functionality and Reference Architecture 

The functions of the DM component can be approximated to the data and knowledge management functionality in Data Lakes or their evolution, Data Lakehouse. A data lake is a scalable storage and analysis system for data of any type, retained in their native format and used mainly for knowledge extraction. It should support the integration of any type of data; support for logical and physical organization of data; accessibility to various kinds of users; metadata catalog to enforce quality and data lineage; governance and scalability in terms of storage and processing. We have systematically surveyed related works and summarized how key data management issues are addressed in DTs, advancing trends and open challenges. We are currently defining the key DM functional components under the big data key value chain and organizing them in an open, reference architecture. 

OSDU Assessment 

We are assessing the OSDU data platform as a means to represent data and metadata, and leverage it as a key technological component for providing DM core functionality for data management DTs in the context of O&G production. Check for preliminary results here.