Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Machine Learning Driven Self-correcting Autonomous Metrology Systems (SAMS)

Summary

As part of the NIST on a Chip program, the autonomous metrology project is developing machine learning driven systems to remove barriers to adoption of advance metrology systems. Towards this end the team is working to apply physics-informed machine learning (ML) to NIST-on-a-Chip (NOAC) sensor measurements to deliver laboratory-grade measurement reliability and accuracy in complex operational environments, effectively putting our expertise and know-how in the field to augment the end-user.

Description

SAMS illustration

The NIST-on-a-chip program has led to the development of a range of disruptive measurement solutions that leverage quantum and (nano)photonic tools to enable traceable measurements that either eliminate or greatly diminish the need for frequent calibrations. However, a successful transition of these technologies from lab to marketplace will depend on a range complex variables including the user-community’s ability to frictionlessly assimilate these technologies into their workflow.

To democratize advanced metrology technologies and make them accessible to all users regardless of expertise, the collaborative effort is focused on the development of machine learning-driven autonomous metrology research systems. The goal is to remove the “PhD-in-the-loop” and accelerate the development of self-correcting quantum and photonic sensor networks. To accomplish this goal our approach relies on combining machine learning with machine-controlled measurement tools for closed loop experiment design, execution, and analysis, where experiment design is guided by active learning, Bayesian optimization, and similar methods. A key challenge is the integration of prior knowledge into the data analysis, including both device physics and material properties.

We are primarily interested in quantum (NV diamond) and photonic sensor networks for thermodynamic metrology (temperature, pressure, and humidity). Team has demonstrated the use of machine learning models to compensate for long-term drift in Fiber Bragg grating based temperature sensors and is currently working on machine-controlled NV diamond spectrometer for pressure, force and dosimetry measurements.

Opportunities

If you are interested in joining our team as a post-doc, guest researcher, collaborator, or student volunteer send us an email.

Created December 9, 2021, Updated April 16, 2024