Research map / Probabilistic and scientific modeling / Differential equations and PDEs
A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling
Jacob Helwig, Sai Sreeharsha Adavi, Xuan Zhang, Yuchao Lin, Felix S. Chim, Luke Takeshi Vizzini, Haiyang Yu, Muhammad Hasnain, Saykat Kumar Biswas, John J. Holloway, Narendra Singh, N. K. Anand and 2 more
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add spatial gradients, CFL features and max pooling to neural CFL inputs (ablation) | neural CFL (ConvNeXt) · Coal dust explosion | one-step MAE of timestep | Improved |
| add the physically-motivated neural CFL enhancements (ablation) | neural CFL (ConvNeXt) · Circular blast | one-step MAE of timestep | No clear effect |
| use U-Net with time-conditioned layer norm backbone | ShockCast · Coal dust explosion and Circular blast | correlation time | Improved |
| use MoE or Euler conditioning with U-Net | ShockCast · Coal dust explosion | TKE error | Improved |
| use F-FNO with Euler or MoE conditioning | ShockCast · Circular blast | TKE error | Improved |
| use DGN instead of MGN backbone | ShockCast · Airfoil Shock | all metrics | Improved |
| use MoE conditioning instead of Affine | neural solver · Coal dust explosion | peak train memory (GiB): 13.465 -> 21.307 | Hurt |
Closest papers by meaning
- MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation (ICML 2025 · similarity 0.85)
- PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows (ICLR 2025 · similarity 0.84)
- Space and time continuous physics simulation from partial observations (ICLR 2024 · similarity 0.83)
- PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling (ICML 2024 · similarity 0.83)
- SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations (ICLR 2024 · similarity 0.82)
- Hierarchical Implicit Neural Emulators (NeurIPS 2025 · similarity 0.82)
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.
