Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEs
Cheng Jing, Uvini Balasuriya Mudiyanselage, Abhishek Verma, Kallol Bera, Shahid Rauf, Kookjin Lee
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 hypernetwork-based modulation to FNOx (ablation) | FNOx · 1D CCP reaction rate | nRMSE: 0.0193 -> 0.0154 | Improved |
| add hypernetwork-based modulation to FNOx (ablation) | FNOx · 1D CCP driving voltage | nRMSE: 0.0345 -> 0.0192 | Improved |
| add input augmentation with physical parameters (pFNOx) to FNOx (ablation) | FNOx · 1D CCP reaction rate | nRMSE: 0.0193 -> 0.0194 | No clear effect |
| add coupled spectral convolution and separate P, W, Q (FNOx) over FNOc | FNOc · 1D CCP reaction rate | nRMSE: 0.0375 -> 0.0193 | Improved |
| add hypernetwork modulation at T_in=1 (ablation) | FNOx · 1D CCP reaction rate | nRMSE: 1.8143 -> 0.1372 | Improved |
| add parameter conditioning at T_in=2 (ablation) | FNOc · 1D CCP reaction rate | nRMSE: 1.0048 -> 0.2151 | Improved |
| reduce input window T_in from 10 to 1 (ablation) | FNOc · 1D CCP reaction rate | nRMSE: 0.0375 -> 1.4484 | Hurt |
| hpFNOx versus HyperFNOc baseline | HyperFNOc · 1D CCP | nRMSE: 0.0278 -> 0.0154 (reaction rate) | Improved |
| apply FNOx variants on Gray-Scott | MWTc · Gray-Scott | relative l2 error: 0.0092 -> 0.0022 | Improved |
Closest papers by meaning
- Maximum Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators (ICML 2025 · similarity 0.90)
- Amortized Fourier Neural Operators (NeurIPS 2024 · similarity 0.89)
- Component Fourier Neural Operator for Singularly Perturbed Differential Equations (AAAI 2024 · similarity 0.88)
- RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains (NeurIPS 2025 · similarity 0.88)
- From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems (ICML 2024 · similarity 0.88)
- Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains (ICML 2024 · similarity 0.87)
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.
