DOE-funded Project Genesis uses deep learning and RL for turbulent-flow modeling
ricardovinuesa · x · 2026-07-23
Researchers from the University of Southern California and Argonne National Laboratory announced Project Genesis, funded by the U.S. Department of Energy.
The project is titled “AI-Driven Subgrid-Scale Model for Large-Eddy Simulation of Turbulent Flows Based on Geometry and Tracking of Turbulence Structures.” Its goal is to combine explainable deep learning and deep reinforcement learning to develop a new turbulence-modeling paradigm for large-eddy simulation.
Related event: DOE Funds Project Genesis for Deep Learning Turbulence Modeling(2 posts)→
More from Research
- WiCV extends ECCV 2026 submission deadline to July 27 — CSProfKGD · 2026-07-23
- Perceptron says its embodied reasoning model beats robotic annotation pipelines on SOTA — AkshatS07 · 2026-07-23
- Retrofitting 3D Objects with Capacitive Sensing: SIGGRAPH 2026 Paper — cholz · 2026-07-23
- SIGGRAPH 2026 method turns 3D objects into multi-touch sensors — cholz · 2026-07-23
- NeurReps 2026 seeks reviewers for its symmetry-and-geometry workshop — fatihdin4en · 2026-07-23
- Agent misbehavior fell to near zero after post-deployment mitigations — Sauers_ · 2026-07-23