Workshop on Cross-Disciplinary Challenges and Opportunities in AI Applications to Science and Engineering (C²OA²SE)

November 6-8, 2024 at MTRI in Ann Arbor, MI

Participant Registration Closes November 4: https://forms.gle/C5PgpbyVcHUfPwnq7

Join us for a collaborative workshop about the common challenges and new frontiers combining science with computing and AI!

Objectives:

• Identify common features of best-in-class AI/ML methods for science
• Characterize approaches for rigorous investigation into complex systems and associated science problems
• Explore engineered systems and the integration of AI into said systems, as well as what this tells us about engineering AI systems

Speakers (Alphabetical):

• Allan Avila (AIMdyn, Inc.)
  Spectral Operator Methods for Learning Dynamical Systems
• Paul Bendich (Geometric Data Analytics and Duke University)
  Shape-based Mathematics at the service of Deep Learning, with applications to AI Safety and Efficient Reinforcement Learning
• Joshua Bloom (UC Berkeley)
  AI in Astrophysics
• Carl Edwards (University of Illinois Urbana-Champaign)
  NLP for Scientific Discovery in Chemistry and Biomedicine
• Santo Fortunato (Indiana University, Bloomington)
  AI in networks and the science of science (provisional)
• Felix Herrmann (Georgia Institute of Technology)
  Digital Twins in the era of generative AI — Application to Geological CO2 Storage
• Bethany Lusch (Argonne National Laboratory)
  AI for Science and Engineering at the Supercomputing Scale
• Ryan McGranaghan (NASA-JPL)
  TBD
• Raphaël Pestourie (Georgia Institute of Technology)
  Scientific Machine Learning for Optimization via Surrogate Models (provisional)
• David Roy (Michigan State University)
  Artificial Intelligence for high spatial resolution satellite fire monitoring
• Steve Techtmann (Michigan Technological University)
  Applications of Machine Learning and Microbial Communities for Environmental Monitoring
• Lingfei Wu (University of Pittsburgh)
  AI for Team Science

Representative Breakout Topics:

• What research areas are still confronted with "too little data" in the era of "too much data"?
• What lessons have we learned about the ways current AI methods FAIL to meet STEM needs?
• What metrics adequately quantify uncertainty in AI output for STEM research purposes?
• How are STEM fields leveraging AI to improve human understanding of complex and previously intractable research problems?
• Is there an inevitable emerging role for interdisciplinary research between computing/computer science and other STEM fields?

Schedule (tentative):

Day 1 (Wednesday, November 6th)

Day 2 (Thursday, November 7th)

Day 3 (Friday, November 8th)

Travel Information:

• MTRI
  3600 Green Ct STE 100, Ann Arbor, MI 48105
• 
  Accommodations
  
  
  
• 
  Directions from DTW
  
  
• 
  Things to Do: Main Street Ann Arbor
  
  

Organizer: S. Kitchen, snkitche@mtu.edu