We propose a data-driven mean-curvature solver for the level-set method. This work is the natural extension to $\mathbb{R}^3$ of our two-dimensional strategy in [arXiv:2201.12342][1] and the hybrid inference system of [DOI: 10.1016/j.jcp.2022.111291][2]. However, in contrast to [1,2], which built resolution-dependent neural-network dictionaries, here we develop a pair of models in $\mathbb{R}^3$, regardless of the mesh size. Our feedforward networks ingest transformed level-set, gradient, and curvature data to fix numerical mean-curvature approximations selectively for interface nodes. To reduce the problem's complexity, we have used the Gaussian curvature to classify stencils and fit our models separately to non-saddle and saddle patterns. Non-saddle stencils are easier to handle because they exhibit a curvature error distribution characterized by monotonicity and symmetry. While the latter has allowed us to train only on half the mean-curvature spectrum, the former has helped us blend the data-driven and the baseline estimations seamlessly near flat regions. On the other hand, the saddle-pattern error structure is less clear; thus, we have exploited no latent information beyond what is known. In this regard, we have trained our models on not only spherical but also sinusoidal and hyperbolic paraboloidal patches. Our approach to building their data sets is systematic but gleans samples randomly while ensuring well-balancedness. We have also resorted to standardization and dimensionality reduction as a preprocessing step and integrated regularization to minimize outliers. In addition, we leverage curvature rotation/reflection invariance to improve precision at inference time. Several experiments confirm that our proposed system can yield more accurate mean-curvature estimations than modern particle-based interface reconstruction and level-set schemes around under-resolved regions.

翻译：我们为级别定置方法建议了一个数据驱动的平均值-曲线求解解解。 这项工作是自然延伸至[ arXiv: 2201. 12342][ 1] 中我们二维战略的$\ mathbb{R ⁇ 3$, 以及[ DOI: 10. 1016/j. jcp. 20222.11191][ 2] 的混合推断系统。 然而, 与[ 1 2 相比, 我们建立了分辨率依赖神经网络的字典, 我们在这里开发了一套模型, $\ mathb{ R ⁇ 3$, 不论直径偏差大小如何。 我们的向前网络, 最向前的向前的向前进网络, 最向前的向前的向前进网络, 向前的向后, 向后, 向前的向下方的向下方, 向前的向下方, 向下方的向下方, 向下方的向下方, 向下方的向下方的向下方, 向下方的向下方, 向下方的向下方的向下方, 向后方的向后方的向后方, 向后方的向后方, 向后方的向后方的向后方, 向后方, 向后方的向后方的向后方, 向后方, 向后方的向后方, 向后方的向后方的向后方, 向后方的向后方, 向后方, 向下方的向后方的向后方的向后方, 向后方的向后方的向下方的向后方的向下方, 向后方, 向后方, 向后方, 向后方, 向后方, 向下方, 向下方, 向下方, 向下方, 向下方, 向下方, 向后方, 向后方的向下方, 向后方的向下方的向下方的向下方的向下方的向下方的向下方的向下方的向下方的向下方的向下方, 向下方的向下方,