Skip to main content

NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.

Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.

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.

Debra Audus (Fed)

Leader, Polymer Analytics Project

Research Interests

Enhanced machine learning

The application of machine learning to polymer physics has traditionally struggled with two major challenges: a lack of large, curated datasets and the need to understand the physics behind the machine learning prediction. Here we aim to simultaneously tackle these challenges through the incorporation of domain knowledge often in the form of theory, thus, providing improved predictions for smaller datasets while improving explainability. This effort is under the Polymer Analytics project.

Circular economy

Polyolefins are the single largest family of polymers produced. Although commonly collected for recycling, sortation of these materials is challenging due to their chemical similarity and architectural diversity. To enable next generation recycling, we combine near-infrared spectroscopy with machine learning to predict polyolefin properties that can then be used for improved sortation. This is a collaborative effort between the Macromolecular Architectures project and the Polymer Analytics project. Additional details can be found at the former link.

Polymer data resources

To spur advances in machine learning for polymer science, we collaborated with external partners to develop the polymeric databases that such algorithms require. In collaboration with MIT, University of Chicago, Citrine Informatics, and Dow we  developed a Community Resource for Innovation in Polymer Technology (CRIPT). This project is led by Prof. Brad Olsen and funded by the NSF Convergence Accelerator. Using FAIR data principles, CRIPT helps users input, visualize and share polymeric data. In collaboration with Prof. Ian Foster, Prof. Juan de Pablo and colleagues at University of Chicago we developed the Polymer Property Predictor and Database. These efforts are under the Polymer Analytics project.

Hydrodynamic properties of dilute particle solutions

We help develop ZENO, a Monte Carlo based code that computes several quantities including the intrinsic viscosity and hydrodynamic radius. It has been previously shown to generate results within experimental uncertainty. More information can be found at https://zeno.nist.gov/

A selected list of publications is below. For a complete list see Google Scholar.

Research Opportunities

Contact me for further details. Current programs include:

SELECTed invited presentations

  • ISM Day, Georgetown University, Washington, DC, 2025
  • Soft Materials, Autonomous Experimentation and Science Policy, Philadelphia, PA, 2025
  • Seminar at University of Maryland, College Park, MD, 2025
  • Artificial Intelligence for Materials Science, Rockville, MD, 2024
  • Seminar at Avery Dennison, Virtual, 2024
  • Seminar at University of Liverpool, Liverpool, UK, 2024
  • Artificial Intelligence for Materials Science, Rockville, MD, 2024
  • Seminar at Avery Dennison, Virtual, 2024
  • Seminar at University of Liverpool, Liverpool, UK, 2024
  • High Polymer Research Group Conference, Pott Shrigley, UK, 2024
  • Seminar at University of Chicago, Chicago, IL, 2024
  • American Physical Society March Meeting, Minneapolis, MN, 2023
  • Seminar at Air Force Research Laboratory, Virtual, 2023
  • UMD Machine Learning for Materials Research Bootcamp and Workshop, College Park, MD, 2023
  • National Academy of Science: Open Access and FAIR Data in the Chemical Sciences webinar, Virtual, 2023
  • Seminar at W.L. Gore & Associates, Inc., Virtual, 2023
  • 33rd IUPAP Conference on Computational Physics, Virtual, 2022
  • Polymer Physics Gordon Research Conference, South Hadley, MA, 2022
  • Materials Research Society Spring Meeting, Virtual, 2022
  • University of Delaware NRT Community Hour, Virtual, 2022
  • CHiMaD/NIST ODI Seminar Series, Virtual, 2022
  • American Physical Society March Meeting, Chicago, IL, 2022

Awards

  • Communications Materials Outstanding Referee, 2023
  • World Materials Research Institutes Forum Young Materials Scientist Finalist, 2014
  • National Research Council Postdoctoral Fellowship, 2013-2015
  • American Physical Society Frank J. Padden Jr. Award Finalist, 2012
  • School for Scientific Thought Fellowship, UC Santa Barbara, 2010
  • Materials Research Laboratory Diversity Fellowship, UC Santa Barbara, 2010
  • Air Products Fellowship, 2010
  • CSP Technologies Fellowship, 2009

Publications

Enabling data-driven design of block copolymer self-assembly

Author(s)
Chiara Magosso, Irdi Murataj, Michele Perego, Gabriele Seguini, Debra Audus, Gianluca Milano, Federico Ferrarese Lupi
Abstract Here we present a database composed of scanning electron microscope images of self-assembled block copolymers. The fabrication process parameters

Data and Software Publications

Theory aware Machine Learning (TaML)

Author(s)
Debra J. Audus, Austin McDannald, Brian DeCost
A code repository and accompanying data for incorporating imperfect theory into machine learning for improved prediction and explainability. Specifically, it focuses on the case study of the

Correlating Near-Infrared Spectra to Bulk Properties in Polyolefins

Author(s)
Bradley P. Sutliff, Shailja Goyal, Tyler B. Martin, Peter A. Beaucage, Debra J. Audus, Sara V. Orski
This repository includes example code and data to correlate near-infrared spectroscopy (NIR) measurements with physical measurements for pure polyolefin samples. Specifically the provided Jupyter
Created July 30, 2019, Updated September 10, 2025
Was this page helpful?