Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.25409

A Unified Interface Neural Network for Elliptic Interface Problems

Qiao Zhuang·Xu Zhang
View original source ↗Read source document ↗Export metadata ↓

Abstract

We develop a Unified Interface Neural Network (UINN) framework for elliptic interface problems with discontinuous coefficients. A single shared network provides a unified representation of the solution in both subdomains, while a projection--correction construction embeds the solution and flux jump conditions directly into the neural trial space. This design aligns with the classical numerical principle of incorporating interfacial physics into the approximation basis to construct interface-unfitted numerical methods. The jump conditions are therefore satisfied exactly for any network parameters. Compared with methods based on separate phase networks and numerical formulations with interface penalty terms, UINN provides a unified representation with exact enforcement of interfacial jump conditions and interface-penalty-free optimization. Those features streamline the numerical formulations and can enhance training robustness. Numerical experiments on smooth interfaces at modestly large and high coefficient contrasts demonstrate UINN's solution accuracy, near-machine-precision satisfaction of the interface jump conditions, and enhanced robustness.

Explore related subjects

physics.comp-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Qiao Zhuang, Xu Zhang. 2026-10-18. A Unified Interface Neural Network for Elliptic Interface Problems. https://arxiv.org/abs/2610.25409

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Physics-informed sampler for solver-free data generation in operator learning

Neural operators offer fast surrogates for parametric PDEs but typically rely on costly datasets generated by repeated numerical solves. We propose a physics-informed sampler (PI-sampler) that generates PDE-consistent input--solution pairs without numerical PDE solves. The sampler draws candidate solution fields from neural-network priors and uses automatic differentiation to evaluate the governing differential, boundary, and initial-condition operators, yielding consistent training tuples by construction. Unlike solution-first methods based on analytical bases or precomputed solutions, it requires neither problem-specific basis functions nor seed simulations. The resulting PDE inputs follow an implicit pushforward distribution, which can be characterized for linear operators in the Gaussian-process limit of Bayesian neural networks but is generally non-Gaussian for nonlinear operators. We integrate the PI-sampler with a function encoder and Transformer-based neural operator and test it on reaction--diffusion equations, Poisson equations on parameterized geometries, time-dependent Sine--Gordon dynamics, a five-dimensional PDE, and flexible-cylinder vortex-induced vibration. The models generalize to independently prescribed forcing distributions, zero forcing, mixed boundary conditions, and unseen geometries. Experiments with DeepONet confirm that the generated data also support other operator architectures. In problem-specific benchmarks, sampling is approximately 51 times faster on CPU and 850 times faster on GPU than numerical solvers. The PI-sampler thus provides an efficient approach to data generation and augmentation that complements high-fidelity simulation.

physics.comp-ph↗
arXiv2026

Repurposing acquisition devices into trigger-based timing synchronization of breakdown events during MITICA high voltage holding experiments

A critical requirement for MITICA -- a full-scale prototype of the heating Neutral Beam Injectors hosted at the Consorzio RFX Neutral Beam Test Facility for the ITER experiment -- is the capability to withstand a continuous voltage of 1MV across the vacuum gaps insulating the beam source from the grounded vessel. To validate such feature, a dedicated voltage-holding test campaign was conducted throughout 2024 and 2025 using a full-scale mock-up of the beam source. The tests also involved an accurate characterization of the associated breakdown events: vacuum dielectric failures which result in rapid potential drops and generate strong current discharges. This contribution will present a relative time reconstruction architecture based on cost-effective, embedded RedPitaya (Zynq-7000 FPGA) devices repurposed as timing hubs. These nodes function as configurable trigger multiplexers while simultaneously recording trigger signals as transients to facilitate the offline reconstruction of event sequences. The method allows self-calibration through measuring the static intrinsic delays of the optical fibers and internal logics, generating delay offsets to synchronize acquired waveforms across a sparse, connected-graph topology of both acquisition devices and hubs themselves.

physics.comp-ph↗
arXiv2026

Proper generalized decomposition with synthetic preconditioning for multiscale parametric phonon transport

Deterministic solution of the phonon Boltzmann transport equation is costly for two reasons: the distribution depends on high-dimensional phase space, and source iteration converges slowly when scattering is frequent. We address both for the steady linearized gray Callaway model in two dimensions by combining proper generalized decomposition (PGD) with the general synthetic iterative scheme (GSIS). The distribution is a sum of products of a space--azimuth factor and a polar factor. This splitting is intrinsically low-rank: along each characteristic the polar angle only stretches the in-plane optical depth, so the rank is bounded, uniformly in the Knudsen numbers, by the numerical rank of the kernel $\exp(-τ/\sinϕ)$. PGD--GSIS updates the factors against a macroscopic source frozen within each alternating step and refreshed by the GSIS moment equations. A Fourier analysis shows that pure PGD, although implicit in the polar factor, moves macroscopic information only through lagged spatial sweeps and stalls like source iteration, whereas the synthetic refresh sees only third-order moments of the representation error. On an isothermal cavity, cross-plane conduction and phonon Poiseuille flow, PGD--GSIS reproduces full-order solutions at ranks 3--14, with heat-flux errors below $6\times10^{-3}$ from the diffusive to the ballistic regime and memory independent of the polar resolution. Treating the inverse Knudsen numbers as coordinates of the polar factor yields one spatial basis over four decades of both; a joint update of all polar factors, which costs only small nodal linear systems, is required for accuracy at large Knudsen numbers.

physics.comp-ph↗