Research map / Probabilistic and scientific modeling / Differential equations and PDEs
(U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs
Nathan Lichtlé, Alexi Canesse, Zhe Fu, HOSSEIN NICK ZINAT MATIN, Maria Laura Delle Monache, Alexandre M Bayen
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 |
|---|---|---|---|
| replace Godunov flux with learned NFV_3^1 flux | finite volume solver · Burgers synthetic | L2 error: 1.9e-3 -> 8.5e-4 | Improved |
| unsupervised weak-form training (UNFV) vs supervised NFV (ablation) | NFV_3^1 · synthetic hyperbolic PDEs | L2 error: Greenshields 1.3e-4 (NFV) vs 2.0e-4 (UNFV); both beat Godunov 4.5e-4 | Mixed |
| enlarge stencil from 3x1 to 5x5 (ablation) | NFV · Burgers synthetic | L2 error: 8.3e-4 -> 2.2e-4 | Improved |
| enlarge stencil from 5x5 to 11x11 (ablation) | NFV · I-24 field data | L1 error: 2.31e-2 -> 2.02e-2 | Improved |
| NFV_3^1 vs ENO/WENO | NFV_3^1 · synthetic PDEs | L2 error: Underwood 3.8e-4 vs WENO 9.8e-5 (WENO better); Greenshields 1.3e-4 vs 6.4e-4 | Mixed |
| NFV vs DG | NFV_5^5 · synthetic PDEs | L2 error: DG 1.0e-4 vs NFV_5^5 2.2e-4 on Burgers | Hurt |
| NFV_11^11 on unseen traffic days vs Godunov | NFV_11^11 · I-24 MOTION unseen days | L2 error: 3.74e-2 -> 2.20e-2 | Improved |
| NFV_3^1 vs calibrated Godunov fits on field data | NFV_3^1 · I-24 MOTION | L1 error: 2.77e-2 -> 2.37e-2 | Improved |
Closest papers by meaning
- UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs (ICML 2024 · similarity 0.87)
- Breakeven complexity: A new perspective on neural partial differential equation solvers (NeurIPS 2026 · similarity 0.86)
- UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss (NeurIPS 2025 · similarity 0.86)
- Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates (ICML 2025 · similarity 0.86)
- MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving (NeurIPS 2026 · similarity 0.85)
- Compute-optimal data scaling for neural surrogates via multi-fidelity training (NeurIPS 2026 · 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.
