Digital Twin Efforts Best Shared, US Government Agencies Told

Major federal agencies, from the U.S. Department of Defense to the U.S. Department of Energy, National Institutes of Health, and the National Science Foundation, need to collaborate to adopt shared digital twin technology to drive their operations, a recent report urges.

“Digital twins hold immense potential to accelerate scientific discovery, drive improvements in climate sciences, and revolutionize health care, manufacturing, and other sectors, but an integrated agenda is needed to harmonize research across sectors and focus efforts on realistic applications,” the report out of the National Academies of Sciences, Engineering, and Medicine states. These efforts should be “crosscutting” to help “advance the mathematical, statistical, and computational foundations underlying digital twin technologies.”

Currently, there is a “lack of adopted standards in data generation” that “hinders the interoperability of data required for digital twins,” the report states, urging “fundamental challenges include aggregating uncertainty across different data modalities and scales as well as addressing missing data.”

To enable such data sharing and collaboration, agencies need to “address challenges such as data ownership and intellectual property issues while maintaining data security and privacy.”

The advantages of cross-agency digital twins are compelling. “The notion of a digital twin has inherent value because it gives an identity to the virtual representation. This makes the virtual representation – the mathematical, statistical, and computational models of the system and its data – an asset that should receive investment and sustainment in ways that parallel investment and sustainment in the physical counterpart.”

See also: Factory Resets: Digital Twins Add New Dimension to Industrial Settings

For example, the National Science Foundation (NSF) “should launch a new program focused on
mathematical, statistical, and computational foundations for digital twins that cuts across multiple application domains of science and engineering,” the report urges. “NSF should encourage collaborations across industry and academia and develop mechanisms to ensure that small and medium-sized industrial and academic institutions can also compete and be successful leading such initiatives.”

The National Institutes of Health (NIH) is also encouraged to “invest in filling the gaps in digital twin technology in areas that are particularly critical to biomedical sciences and medical systems. These include bioethics, handling of measurement errors and temporal variations in clinical measurements, capture of adequate metadata to enable effective data harmonization, complexities of clinical decision-making with digital twin interactions, safety of closed-loop systems, privacy, and many others.”

Digital twin collaboration requires trust

The report also emphasizes the key role of verification, validation, and uncertainty quantification (VVUQ) in ensuring trust in the digital twin resources being shared. However, there is a lack of standards in reporting VVUQ “as well as a lack of consideration of confidence in modeling outputs.”

VVUQ ensures trust between different groups accessing digital twin data and configurations. “It is critical that VVUQ be deeply embedded in the design, creation, and deployment of digital twins,” the report states.

Fostering a trusted culture of collaborative exchange of data and models across agencies that incorporate context through metadata and provenance in digital twin–relevant disciplines “could accelerate progress in the development and application of digital twins,” the report’s authors argue.

Digital twins are seen as a step up from previous data modeling approaches that are already common across federal agencies. “A digital twin is distinguished from traditional modeling and simulation in the way that models and data work together to drive decision-making,” the report states. “An important need is to advance hybrid modeling approaches that leverage the synergistic strengths of data-driven and model-driven digital twin formulations.”