Support Options

Report a problem

About you
This is a randomly generated image of letters and numbers. Letters not clear? Click to renew CAPTCHA.
About the problem

NSF CHE/DMS Innovation Lab: Learning the Power of Data in Chemistry

Join Policy
Invite Only
14 Sep 2018

We invite chemists, chemical engineers, statisticians, applied mathematicians, and computer scientists to apply for the

NSF CHE/DMS Innovation Lab: Learning the Power of Data in Chemistry

A host of new opportunities for chemists and data scientists is envisioned for data science and chemistry to interchange ideas, develop new methods, and address long-standing problems. Chemistry has always been a data-driven science, but recent advances in chemical analysis, synthesis, and modeling are providing a deluge of new data that are multimodal, multi-scale, and heterogeneous. Effective collection, analysis, and interpretation of this data has the potential to catalyze new directions and provide transformative solutions to some of the greatest challenges of the 21st century. In this Innovation Lab, 20 chemists and 20 data science researchers will meet face to face, learn to speak each others languages, and begin collaborative projects on site. A mini-bootcamp will be organized to provide a training ground for participants to familiarize them with chemical and data-science challenges and approaches.

The CHE/DMS Innovation Lab's goals include

  1. Identifying transformative data-driven research topics, strategies, and methodologies that will advance the foundations of Chemistry and Data Science
  2. Fostering interdisciplinary collaborations that leverage data-driven approaches for emerging research problems in Chemistry
  3. Creating a vibrant research community that brings together Data Science and Chemistry on a long-term basis

What is an Innovation Lab?

An Innovation Lab is a deliberate, creative, process of generating novel research ideas. Applicants with a variety of expertise are brought together, with professional facilitators and senior scientists to assist the participants throughout the experience. Working with the assistance of these mentors, participants attend a mini-bootcamp centered on data sources and data tools, frame new research questions, generate novel – and risky – research ideas, form interdisciplinary teams around these ideas, prototype the ideas, and finally develop them into interdisciplinary proposals to address the challenge at hand.
Ultimately, this Innovation Lab will form a strong foundation for continued interdisciplinary research at the interface between data science and chemical sciences.

Who should apply to attend the lab?

Data scientists and chemists who are ready to learn new ways of thinking, address major scientific challenges, and collaborate on exciting interdisciplinary projects.
Data science participants are not expected to have prior knowledge or experience with chemistry data.
Chemists should apply from all areas, especially those in areas not historically represented by data initiatives (i.e., the lab will not emphasize drug design, materials, or genomes). 
Data scientists should apply from wide variety of areas, especially from machine learning, computer science, statistics, applied mathematics, and other related fields.
Applicants with diverse backgrounds are especially encouraged to apply.

When and where will the lab be held?

The lab will be held in Airlie House (, just outside of Washington, DC, from December 17th through the 21st. 

Who is organizing the lab?

Steering committee:
Xiaoming Huo, Georgia Tech
Paul Zimmerman, University of Michigan
Mihai Anitescu, Argonne National Lab
Ilse Ipsen, North Carolina State University (
Carlos Gonzalez, NIST
Josh Schrier, Fordham University
Aarti Singh, Carnegie Mellon University

Facilitation and organization:
Know Innovation


Next steps

Please watch the recording of our webinar.  Click here to watch the webinar, and then complete the application form, using this link Link to application form.

Applications are due October 26th, 2018, at 8PM Eastern Time.



This meeting is supported by a grant from the National Science Foundation (1848701) through the Divisions of Chemistry (CHE) and Mathematical Sciences (DMS). The views expressed in this webpage do not necessarily represent the views of the NSF.

The opinions, findings, and conclusions or recommendations expressed on this site are those of the author(s) and do not necessarily reflect the views of Knowinnovation Inc.