CCRG Colloquium: Learning from simulations using ML/AI tools

CCRG Colloquium
Learning from simulations using ML/AI tools

Register for Zoom Link Here

Dr. Viviana Acquaviva
Professor, Physics Department
CUNY NYC College of Technology

Event Details:
Recent developments in machine learning and AI have given us a new set of tools to answer science questions, while creating new challenges in terms of trust and interpretability. My research focuses on the process of learning from simulations using these tools. I will show a few examples from my Astrophysics work, on validating cosmological simulations and formulating hypotheses for the physical model that drives galaxy evolution processes. I will then move on to current research in climate science, where we are developing custom metrics to assess similarity in climate models outputs, and using representation learning to reconstruct full spatiotemporal fields from sparse and biased ocean data. I will conclude with some lessons learned in applying AI across disciplines, and some considerations on how a careful study of AI systems can help remedy the lack of transparency of AI-based models.

Bio:
I am a Professor in the Physics Department at the CUNY NYC College of Technology and at the CUNY Graduate Center, an adjunct Senior Research Scientist at Columbia University and the Lamont-Doherty Earth Observatory, and a Visiting Professor at the SISSA Institute for Data Science and at the Flatiron Institute. I wrote an introductory textbook on Machine Learning techniques for Physics and Astronomy for Princeton University Press that won the 2024 Chambliss Astronomical Writing award. I am interested in using Data Science tools to improve climate models and find climate solutions, with two broad research directions: 1) Evaluating similarity in the output of climate models and 2) Reconstructing full spatio-temporal fields, in particular ocean carbon, from limited and biased data. I am also reflecting on how scientists can foster a more responsible AI revolution and how principles of ethical AI can be translated into an actionable framework for scientists. Since October 2023, I have been a member of the Italian AI Advisory Council, tasked by the Italian government with proposing an updated national strategy for AI.

Intended Audience:
All are Welcome!

To request an interpreter, please visit myaccess.rit.edu