基于动态谱优化的Si基外延SrTiO3忆阻器氧空位动力学的物理信息神经网络代理模型
Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial $\mathrm{SrTiO_3}$ on Si memristors via Dynamic Spectral Optimization
查看机构详情
- Texas State University（德克萨斯州立大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对Si基外延SrTiO3忆阻器氧空位动力学的建模难题，本文提出级联PINN架构结合DSO V2 Hybrid优化器，构建的代理模型精度高且推理效率优于COMSOL。
中文摘要 AI 辅助
物理信息神经网络（PINNs）为半导体器件建模提供了有前景的框架，但标准架构难以应对氧化物异质结构固有的严重数值刚度和多尺度空间差异。本文展示了一种级联PINN架构，结合定制的二阶切比雪夫第二类多项式谱优化器（DSO V2 Hybrid），用于建模Pt/SrTiO3/Si忆阻异质结构中的离子-电子漂移-扩散输运，该结构跨越380μm Si衬底上的20nm STO薄膜。通过将电势、载流子密度和空位输运分离为四个顺序训练的子神经网络，我们的模型无需算子分裂即可规避超过10^16的条件数。训练后的代理模型再现了实验导电原子力显微镜的电流-电压滞回特性（R²>0.96），同时确保连续空间内严格的泊松一致性。与传统有限元求解器（如COMSOL）相比，该PINN代理支持可微逆参数估计和线性时间推理。
英文摘要
Physics-informed neural networks (PINNs) offer a promising framework for modeling semiconductor devices, yet standard architectures struggle with severe numerical stiffness and multiscale spatial discrepancies inherent to oxide heterostructures. Here, we demonstrate a cascaded PINN architecture coupled with a custom second-order Chebyshev second kind polynomial spectral optimizer (DSO V2 Hybrid) to model ion-electronic drift-diffusion transport in Pt/SrTiO$_3$/Si memristive heterostructures across a 20 nm STO film on a 380 $μ$m Si substrate. By isolating potential, carrier density, and vacancy transport into four sequentially trained sub-neural-networks, our model circumvents condition numbers exceeding $10^{16}$ without operator splitting. The trained surrogate reproduces experimental conductive-AFM current-voltage hysteresis ($R^2 > 0.96$) while ensuring strict Poisson consistency across continuous space. Compared to conventional finite-element solvers (e.g., COMSOL), the PINN surrogate enables differentiable inverse parameter estimation and linear time inference.
