EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diffusion-regularized PINNs for Poisson inverse source reconstruction of charge dynamics from noisy potential measurements

Jungmin Kim, Dongin Yang, Minbaek Lee

AIP Advances · 01.06.2026 · 16 (6)

DOI: 10.1063/5.0320619 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 10.06.2026. Verfasst von Jungmin Kim und 2 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Inha University, Ministry of Science and ICT, South Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reconstructing spatiotemporal charge density from noisy potential measurements (e.g., Kelvin probe force microscopy) is a fundamental inverse problem in semiconductor characterization, yet it is severely ill-posed because charge is proportional to the Laplacian of the potential, which amplifies high-frequency noise. Conventional approaches typically require smoothing or explicit initial/boundary conditions (IC/BC) to stabilize solutions; however, such priors are often unavailable in realistic experiments. Here, we propose a Poisson–diffusion inverse physics-informed neural network (PD-iPINN) that couples the quasi-static Poisson equation with a diffusion–decay dynamics constraint for charge transport. Crucially, we train PD-iPINN without IC/BC loss terms, using only potential observations over space–time and PDE residuals. Across systematic synthetic test cases (1D sinusoidal, 1D Gaussian, and 2D sinusoidal charge dynamics) with relative Gaussian noise levels up to 100%, PD-iPINN achieves substantially improved charge reconstruction compared to a Poisson inverse PINN (P-iPINN), reducing relative L2 error by 1.8–2.4× at 50% noise and 3.0–4.8× at 100% noise while maintaining comparable potential fitting. PD-iPINN also exhibits strong grid robustness, retaining relative L2 error below 0.3 at 50% noise even on sparse spatial grids (Nx=21). In parameter estimation tests, the decay rate k is reliably identified (≤8% error at 100% noise), whereas the diffusion coefficient D is more noise-sensitive. We interpret the improved stability as diffusion-induced temporal regularization that suppresses high-frequency components in Fourier space, synergizing with neural networks’ spectral bias. The proposed framework provides a practical route to IC/BC-free charge dynamics reconstruction from noisy potential data.

Förderung

  • Inha University
  • Ministry of Science and ICT, South Korea

Zitieren

APA

Kim, J., Yang, D., & Lee, M. (2026). Diffusion-regularized PINNs for Poisson inverse source reconstruction of charge dynamics from noisy potential measurements. AIP Advances, 16(6). https://doi.org/10.1063/5.0320619

Vancouver

Kim J, Yang D, Lee M. Diffusion-regularized PINNs for Poisson inverse source reconstruction of charge dynamics from noisy potential measurements. AIP Advances. 2026;16(6). doi:10.1063/5.0320619

BibTeX
@article{Kim2026,
  author = {Kim, Jungmin and Yang, Dongin and Lee, Minbaek},
  title = {Diffusion-regularized PINNs for Poisson inverse source reconstruction of charge dynamics from noisy potential measurements},
  journal = {AIP Advances},
  year = {2026},
  volume = {16},
  number = {6},
  doi = {10.1063/5.0320619}
}
Kostenlos starten →