unknown
Discrepancy Modeling with Physics Informed Machine Learning
Steven L Brunton
Abstract
This video describes how to combine machine learning with classical physics models to correct for discrepancies in the data (e.g., from nonlinear friction, wind resistance, etc.). Several examples are covered, from modern robotics, to classical connections with Galileo v. Aristotle, and Kepler v. Ptolemy. The examples in this video highlight work and discussions with Prof. Nathan Kutz, especially connections to classical scientific discoveries. SLB acknowledges support from the National Science Foundation AI Institute in Dynamic Systems (grant number 2112085).
Sourced from arXiv · Updated September 2, 2026
Thank you to arXiv for use of its open access interoperability.
View original source ↗Spot an error on this page? Let us know →FAQ
Common questions
What is "Discrepancy Modeling with Physics Informed Machine Learning" about?
This video describes how to combine machine learning with classical physics models to correct for discrepancies in the data (e.g., from nonlinear friction, wind resistance, etc.). Several examples are covered, from modern robotics, to classical connections with Galileo v. Aristot
Who wrote this paper?
Steven L Brunton
Where can I read the full paper?
The full text is available as a PDF on arXiv (linked above), published August 5, 2022.
Does this paper have a DOI?
Yes: 10.52843/cassyni.ftzlk9.