Tag
Introduces Weak-form Kernel Ridge Regression (WKRR) for learning dynamical systems from noisy measurements, combining a weak formulation with kernel ridge regression to filter noise and improve accuracy. The method outperforms baseline methods on chaotic benchmarks up to 64 dimensions and 15,000-dimensional real-world fluid data.
This paper presents open multimodal datasets and open-source software packages for reproducible AI-enabled thermal-fluid research, introducing a spatial-temporal dimensionality framework and tools like SeqReg for sequence regression.