Research map / Probabilistic and scientific modeling / Dynamical systems
Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty
Luning Sun, Daniel Zhengyu Huang, Hao Sun, Jian-Xun Wang
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 |
|---|---|---|---|
| Use BSL instead of RVM | Equation discovery · Van der Pol oscillator, 5% noise | rmse (×10^-3): 27.46 -> 18.04 | Improved |
| Use BSL instead of RVM | Equation discovery · Lorenz 96, 10% noise | rmse (×10^-3): 49.7 -> 13.0 | Improved |
| Use BSL instead of PINN-SR | Equation discovery · Advection equation, 20% noise | rmse (×10^-3): 30.4 -> 1.9 | Improved |
| Use BSL instead of PINN-SR | Equation discovery · Burgers' equation, 10% noise | rmse (×10^-3): 10.3 -> 6.38 | Improved |
| Use BSL instead of PINN-SR | Equation discovery · Burgers' equation with source, 20% noise | rmse (×10^-3): 34.6 -> 13.4 | Improved |
| Use BSL instead of SINDy | Equation discovery · Heat equation, 15% noise | rmse (×10^-3) | Improved |
| Use BSL instead of SINDy | Equation discovery · Poisson equation, 5% noise | rmse (×10^-3): 962 -> 16.7 | Improved |
| Assimilate observations with EnKF using the discovered model | Lorenz 96 forecasting · Lorenz 96 chaotic forecast | prediction accuracy | Improved |
Closest papers by meaning
- Differentiable Sparse Identification of Lagrangian Dynamics (AAAI 2026 · similarity 0.89)
- The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling (NeurIPS 2026 · similarity 0.86)
- Symmetry-Informed Governing Equation Discovery (NeurIPS 2024 · similarity 0.85)
- Bayesian Adaptive Calibration and Optimal Design (NeurIPS 2024 · similarity 0.85)
- Learning Macroscopic Dynamics from Partial Microscopic Observations (NeurIPS 2024 · similarity 0.85)
- Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations (NeurIPS 2025 · 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.
