NIST - Manufacturing Technology Roadmapping

AI-Enhanced Multimodal Sensing of Materials and Processes for Complete Product Lifecycle Performance

Roadmap Overview


With recent advances in artificial intelligence (AI) and machine learning (ML) over the past few years, alongside improvements in distributed sensing, Internet of Things (IoT), and Edge Computing, there is a tremendous opportunity to combine AI/ML with physical domain knowledge (materials, processes, etc.) for manufacturing. This integration would make it possible to leverage the multi-scale, multimodal data streams from across a product’s service life to achieve significant improvements at each stage in its lifecycle, from materials synthesis and selection, to product design, manufacturing, deployment, and eventual retirement and/or recycling.

This roadmap sets out a vision for this desired future state, identifies major challenges and opportunities related to achieving the vision, and provides a set of implementation plans for overcoming the challenges and realizing the benefits of AI-enhanced multimodal sensing of materials and processes for complete product lifecycle performance.

Goals and Objectives

This roadmap establishes a plan to develop multimodal sensing and AI/ML-driven closed-loop control capabilities and data insights to help manufacturers improve full product lifecycle performance. There are four key objectives to enable this goal:

  1. Integrate Multimodal Data Over Multiple Timescales (throughout the product lifecycle)
  2. Capture Domain Insights from Materials Science and Manufacturing to guide Core Technology Developments
  3. Develop Feedback Strategies over Multiple Timescales that impact Materials Synthesis and Selection, Product and Process Design, Process Control, Product Service Life, and Retirement
  4. Develop Core Technologies necessary to achieve the vision (AI/ML, Multimodal Sensing and Imaging, Process Control and Automation, Physics-based Computational Models)

Core Focus Areas

The core focus areas for this roadmap are:

  1. Sensing, Data Acquisition & Data Management Across the Product Lifecycle
  2. Applications of AI/ML & Data Analytics Across the Product Lifecycle
  3. Comprehensive Integration of Data and AI/ML Insights Across the Product Lifecycle

Roadmap Release - February 27, 2024

We will also hold initial planning discussions for a proposed consortium, as the activities proposed in this roadmap are beyond the scope, funding, and capabilities of any single organization. Achieving the roadmap’s vision will require the coordinated efforts of a multistakeholder consortium, and we invite those interested in shaping and driving that consortium to attend and contribute.   

The release event will include an overview of the roadmap, including the critical challenges and opportunities, as well as specific recommendations for research and development activities to begin building the needed Tools & Equipment, Standards & Techniques, and Training & Educational Resources.

To REGISTER and learn more about this in-person event, click here.

Please contact Nick Barendt for additional information.

Download Roadmap

Download A Manufacturing Technology Roadmap for AI-Enhanced Multimodal Sensing of Materials and Processes for Complete Product Lifecycle Performance.

Roadmap Committee

This effort was lead and organized by:

Nexight Group supported the overall roadmapping process and helped to prepare the roadmap document.

Mike Yost led consortium-related activities.

Roadmap Contributors

Paul Ardis

General Electric

Mehmet Aydeniz

University of Tennessee, Knoxville

Nick Barendt*

Case Western Reserve University

Bernard Bewlay

General Electric

David Bourne

Carnegie Mellon University

Jackie Bowen*

Nexight Group

Brad Boyce

Sandia National Laboratories

Ross Brindle*

Nexight Group

Jian Cao

Northwestern University

Jennifer Carter

Case Western Reserve University

Vipin Chaudhary

Case Western Reserve University

Hikmat Chedid

Lorain County Community College

Clayton Cooper

Case Western Reserve University

Brian DeCost

National Institute of Standards and Technology (NIST)

Scott Drinkall*

Nexight Group

Robert Foy*

Nexight Group

Wentao Fu

Boeing Additive Manufacturing (BAM) Intelligence Center

Robert Gao*

Case Western Reserve University

Joseph Giampapa

ARM Institute

Charles Gifford

21st Century Manufacturing Solutions

Michael Grieves

Digital Twin Institute

Mike Groeber

Ohio State University

Markus Heinimann


David Icove

University of Tennessee, Knoxville

Mahdi Jamshid

ASTM International

Reeja Jayan

Carnegie Mellon University

Xiaodong Jia

University of Cincinnati

Jared Kosters*

Nexight Group

Dominik Kozjek

Northwestern University

John Lewandowski*

Case Western Reserve University

Ken Loparo*

Case Western Reserve University

Norbert Majerus

Norbert Majerus Consulting LLC

Jim Maloney


Michael McClellan

Collaboration Synergies, Inc.

Jack McNulty


Nikunj Mehta

Falkonry AI

KC Morris

National Institute of Standards and Technology (NIST)

Steve Niezgoda

Ohio State University

Vincent Paquit

Oak Ridge National Laboratory

Joseph Powell

Akron Steel Treating (AST)

Clare Rimnac

Case Western Reserve University

Tony Rollett

Carnegie Mellon University

Andrew Saku*

Nexight Group

Michael Skocik

ARM Institute

Peng Wang

University of Kentucky

Jim Warren

National Institute of Standards and Technology (NIST)

Jonathan Wise

Clean Energy Smart Manufacturing Innovation Institute (CESMII)

Sarah Wolff

Ohio State University

Mike Yost*


Jianjang Zhang

Case Western Reserve University

* = internal roadmap development team

Funding Acknowledgement

This work was performed under financial assistance award #70NANB22H049 from U.S. Department of Commerce, National Institute of Standards and Technology.