Error-correcting neural networks for semi-Lagrangian advection in the level-set method

TL;DR

This paper introduces a neural network-enhanced semi-Lagrangian level-set method that reduces numerical diffusion and mass loss by on-the-fly, data-driven corrections, improving efficiency and accuracy in interface advection tasks.

Contribution

It presents a novel machine learning framework that integrates neural network corrections into the level-set advection process, focusing computational effort near the interface for improved accuracy and efficiency.

Findings

Achieves same precision as high-resolution schemes at half the resolution.

Effectively counters numerical diffusion and mass loss in advection.

Enhances interface tracking in complex flow scenarios.

Abstract

We present a machine learning framework that blends image super-resolution technologies with passive, scalar transport in the level-set method. Here, we investigate whether we can compute on-the-fly, data-driven corrections to minimize numerical viscosity in the coarse-mesh evolution of an interface. The proposed system's starting point is the semi-Lagrangian formulation. And, to reduce numerical dissipation, we introduce an error-quantifying multilayer perceptron. The role of this neural network is to improve the numerically estimated surface trajectory. To do so, it processes localized level-set, velocity, and positional data in a single time frame for select vertices near the moving front. Our main contribution is thus a novel machine-learning-augmented transport algorithm that operates alongside selective redistancing and alternates with conventional advection to keep the adjusted interface trajectory smooth. Consequently, our procedure is more efficient than full-scan convolutional-based applications because it concentrates computational effort only around the free boundary. Also, we show through various tests that our strategy is effective at counteracting both numerical diffusion and mass loss. In simple advection problems, for example, our method can achieve the same precision as the baseline scheme at twice the resolution but at a fraction of the cost. Similarly, our hybrid technique can produce feasible solidification fronts for crystallization processes. On the other hand, tangential shear flows and highly deforming simulations can precipitate bias artifacts and inference deterioration. Likewise, stringent design velocity constraints can limit our solver's application to problems involving rapid interface changes. In the latter cases, we have identified several opportunities to enhance robustness without forgoing our approach's basic concept.