Research map / Probabilistic and scientific modeling / Dynamical systems
Deep Dynamical Modeling and Control of Unsteady Fluid Flows
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train the dynamics model with recursive multi-step predictions rather than single-step predictions (ablation) | Deep Koopman · Cylinder flow, 32-step sequences | relative prediction error over time | Helped |
| Use a learned Koopman-invariant state mapping for prediction | Deep Koopman · Cylinder flow, beyond the 32-step horizon | relative prediction error | Helped |
| Replace the Deep Koopman model with Deep VBF | Unforced cylinder-flow modeling · Cylinder flow, beyond the 32-step horizon | relative prediction error | Hurt |
| Apply proportional control using y-velocity at the location d* | Cylinder flow control · Cylinder flow at Reynolds number 50 | momentum residuals | Helped |
| Move the proportional-control measurement location to 1/2 d* or 2 d* | Cylinder flow control · Cylinder flow at Reynolds number 50 | momentum residuals | Hurt |
Closest papers by meaning
- Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize (ICLR 2021 · similarity 0.84)
- Learning Reduced Fluid Dynamics (AAAI 2024 · similarity 0.83)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024 · similarity 0.83)
- Aerodynamic Coefficients Prediction via Cross-Attention Fusion and Physical-Informed Training (AAAI 2025 · similarity 0.81)
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows (NeurIPS 2026 · similarity 0.81)
- DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization (NeurIPS 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.