Scholar
Michael McCabe
Google Scholar ID: SMXfsHYAAAAJ
Flatiron Institute
Citations & Impact
Citations
365
H-index
8
i10-index
8
Publications
20
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- 2023/12/18 - MPP won best paper at the NeurIPS 2023 Workshop on AI for Science!; 2023/12/08 - Our paper on stability of neural operators was accepted to TMLR!; 2023/10/09 - Released work on multiple physics pretraining with the PolymathicAI collaboration to arxiv!; 2023/06/22 - Released joint work with Peter and Shashank from LBL on stability in autoregressive neural operators on arxiv!; 2021/9/28 - The updated version of our earlier workshop paper, now titled, “Learning to Assimilate in Chaotic Dynamical Systems” was accepted to NeurIPS 2021.
Research Experience
- Currently a research engineer at the Polymathic team of the Flatiron Institute; previously worked as a Data Scientist in industry, applying machine learning to solve real-world problems in healthcare, finance, and energy sectors; collaborated with Lawrence Berkeley National Lab on deep learning-based weather models in summer 2022; worked as a Givens associate at Argonne National Lab in summer 2021.
Education
- Ph.D. from the University of Colorado, Boulder, under Prof. Jed Brown, focusing on machine learning for computational physics, including data assimilation, dynamics modeling, and large-scale deep learning.
Background
- Research interests: machine learning and optimization. Particularly interested in ML for physics-driven systems, leveraging prior knowledge of system behavior in the form of PDEs, invariances, or conservation laws. Brief introduction: A researcher at the Flatiron Institute's Polymathic team, focusing on deep learning for the physical sciences.
Miscellany
- Hobbies include climbing, running, and reading.
