Research map / Probabilistic and scientific modeling / Molecules and proteins
Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data
Wai Tong Chung, Bassem Akoush, Pushan Sharma, Alex Tamkin, Ki Sung Jung, Jacqueline Chen, Jack Guo, Davy Brouzet, Mohsen Talei, Bruno Savard, Alexei Y Poludnenko, Matthias Ihme
Read the paperCheck your idea against 137,217 papers
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 gradient-based physics loss to RRDB (ablation) | RRDB · Momentum128 baseline test, 8× SR | SSIMρ,u: 0.907±0.003 -> 0.936±0.003 | Improved |
| Add gradient-based physics loss to RRDB (ablation) | RRDB · Momentum128 parametric variation, 8× SR | SSIMρ,u: 0.898±0.003 -> 0.929±0.001 | Improved |
| Add gradient-based physics loss to RRDB (ablation) | RRDB · Momentum128 baseline test, 8× SR | NRMSEρ,u: 0.92±0.01 -> 0.60±0.00 | Improved |
| Add gradient-based physics loss to RRDB (ablation) | RRDB · Momentum128 baseline test, 8× SR | NRMSE E^k: 0.39±0.10 -> 0.41±0.17 | Hurt |
| Increase SR ratio from 16× to 32× | RRDB + gradient loss · Momentum128 baseline test | SSIMρ,u: 0.739±0.008 -> 0.505±0.001 | Hurt |
| Use learned SR instead of tricubic interpolation | RRDB · Momentum128 baseline test, 32× SR | SSIMρ,u: 0.508 -> 0.503±0.001 | Hurt |
| Use learned SR instead of tricubic interpolation | RRDB · Momentum128 baseline test, 32× SR | SSIMsgs: 0.060 -> 0.194±0.005 | Improved |
| Use RCAN rather than EDSR or vanilla RRDB at smaller model sizes | 3D turbulent-flow SR models · Momentum128, model sizes below 17M parameters | SSIM | Improved |
| Scale up Conv-FNO beyond approximately 20M parameters | Conv-FNO · Momentum128 SR | SSIMsgs | Improved |
Closest papers by meaning
- EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale (NeurIPS 2025 · similarity 0.88)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024 · similarity 0.88)
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows (NeurIPS 2026 · similarity 0.87)
- Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows (NeurIPS 2026 · similarity 0.86)
- PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction (ICML 2025 · similarity 0.86)
- The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning (NeurIPS 2024 · similarity 0.85)
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.
