Nicholas A. Gabriel

CV | Google Scholar | GitHub | LinkedIn

About Me

I am a PhD candidate in the Physics Department at The George Washington University. I study complex systems using informed AI/ML techniques, with a particular emphasis on social dynamics and influence. This work takes place at the intersection of the social sciences, complex systems physics, and informed AI. We are investigating the next generation of neural tools to leverage and explain large-scale social system data.

A major theme of my research is the interplay between complex systems physics and AI techniques: developing novel architectures for solving inverse problems in complex systems, and designing neural analogs of techniques used in complex systems. The most useful neural techniques for modeling complex systems come from graph learning and operator learning, and I design neural "glue" between these architectures such that different representations can inform one another.

In my spare time I enjoy cycling, making espresso, and watching train videos.

Publications

• Connecting the geometry and dynamics of many-body complex systems with message passing neural operators.
  Nicholas A. Gabriel, Neil F. Johnson, George Em Karniadakis
  arXiv preprint, 2025.
• Inductive detection of Influence Operations via Graph Learning.
  Nicholas A. Gabriel, David A. Broniatowski, Neil F. Johnson
  Scientific Reports, 2023.
• Using Neural Architectures to Model Complex Dynamical Systems.
  Nicholas A. Gabriel, Neil F. Johnson
  Advances in Artificial Intelligence and Machine Learning, 2022.
• Online hate network spreads malicious COVID-19 content outside the control of individual social media platforms.
  Nicolas Velasquez, Rhys Leahy, Nicholas Restrepo, Yonatan Lupu, Richard Sear, Nicholas Gabriel, Om Jha, Beth Goldberg, Neil Johnson
  Scientific Reports, 2021.
• The online competition between pro- and anti-vaccination views.
  Neil Johnson, Nicolas Velásquez, Nicholas Restrepo, Rhys Leahy, Nicholas Gabriel, Sara El Oud, Minzhang Zheng, Pedro Manrique, Stefan Wuchty, Yonatan Lupu
  Nature, 2020.
• Quantifying COVID-19 content in the online health opinion war using machine learning.
  Richard F Sear, Nicolás Velásquez, Rhys Leahy, Nicholas Restrepo, Sara El Oud, Nicholas Gabriel, Yonatan Lupu, Neil Johnson
  IEEE Access, 2020.

Presentations

• The George Wasington University (ENIGMA seminar, 45m presentation) [slides]
  "Multiscale Operator Learning for complex social systems", 10/4/2023.
• Brown University (CRUNCH group meeting, 40m presentation) [slides]
  "Multiscale Operator Learning for complex social systems", 9/15/2023.
• IC2S2 2022 (Conference talk, 15m presentation) [slides]
  "Automated Detection of Information Operations Using Graph Neural Networks", 7/21/2022.
• Brookhaven National Laboratory (PROSPECT group meeting, 20m presentation) [report]
  "Mass calibration for PROSPECT", 8/10/2016.