Machine learning models show consistent errors near peaks in fluid flow simulations
Structured Extrema Errors in Classical Surrogates for Viscous Burgers: A Physics-Consistent Interpretation
Machine Learning
Summary
Simulating how fluids flow can be tricky, especially when using machine learning models to predict changes over time. The authors studied several common types of models predicting the behavior of a simple fluid equation and found that all of them make similar mistakes near the highest and lowest points in the flow. For some models, this error is linked to how well the model captures the smoothness or curvature of the flow. They discovered that improving the model’s handling of this curvature can reduce errors not just immediately, but also when making longer predictions step by step.
viscous Burgers equationmachine learning surrogateradial basis functionkernel ridge regressionlocal curvatureviscous smoothingadvection and diffusionprediction errorfluid simulationrecursive rollout
Authors
Youssef Oubari
Abstract
We study the local errors of classical machine-learning surrogate models, which approximate the time evolution of the one-dimensional viscous Burgers equation. Four models are compared on the same prediction task, using the spatial grid values directly: radial basis function (RBF) kernel ridge regression (KRR), linear Ridge, ExtraTrees, and Random Forests. Across all four models, the one-step residual, defined here as the true value minus the predicted value at each grid point, forms clear curved branches near predicted maxima and minima. A more detailed analysis of KRR shows that these errors are much more strongly related to the second spatial derivative, which measures local curvature, than to the first spatial derivative. Near a smooth extremum, predicted value and curvature form a local two-branch fold. Under our local curvature-based model of the residual, this fold predicts a leading-order near-parabolic relation between predicted value and residual. This geometric result motivates a direct test of the Burgers advection (transport) and diffusion (smoothing) terms. For KRR and Ridge, regression tests on held-out trajectories, a control that breaks the spatial alignment of the diffusion term, and a spectral test of high-frequency content are consistent with insufficient viscous smoothing at moderate and high viscosity. In this case, the surrogate retains more small-scale structure than the true future state. The same physical explanation is much weaker for the tree models. Finally, a correction that uses only predicted quantities reduces both one-step error and error during recursive rollout, where each prediction is used as the next input.