A Physics-Chemistry-Informed Neural Network (PCINN) for Real-Time Spatial-ALD Coverage Prediction and Reliable Kinetics Inversion

2026/07/31 by Ning Hu, Chang Liu, Yunlei Jiang +1
Computer Science · Physics and Astronomy · #cs.LG #physics.comp-ph

paper · pdf

31 pages, 12 figures, 8 tables

arxiv created 2026/07/31 · arxiv updated 2026/08/04

Abstract

Spatial atomic layer deposition (SALD) is a leading atmospheric-pressure, high-throughput route to industrial ALD, but design and control are limited by the cost of predicting surface coverage: high-fidelity CFD is far too slow for operating-window scans, while analytic models miss transport modulation such as the gas curtain. We present a physics-chemistry-informed neural network (PCINN), a hybrid surrogate with CFD-level accuracy at real-time speed: a query returns coverage in about 7 ms, roughly 5x10⁴ times faster than a CFD solve, reaching a test R²_log = 0.998 (leave-one-out R²_raw = 0.974) from only 30 training cases spanning four orders of magnitude in coverage. The architecture is not a black box: a small network learns only the operating-condition to near-wall concentration closure, while the known surface kinetics is a hard-coded, trainable chemistry layer integrated along the substrate trajectory. This single-scalar bottleneck keeps it accurate under sparse data, interpretable and invertible. We add a full identifiability analysis (Fisher information, profile likelihood). The adsorption energy E_ads and desorption rate k_des are robustly identifiable; k_ads is not separately identifiable at a single temperature (only k_ads*c_wall is). Across four temperatures the prefactor nu and E_ads bind along a weakly identifiable degeneracy valley of slope 0.065 eV/decade, derived analytically as k_B T_eff ln(10) and turned into a reliability diagnostic: a seven-chemistry mismatch matrix shows it is invariant under any single-Arrhenius mismatch and shifts only when a second thermally activated process appears, so a slope departure flags unmodelled site heterogeneity. Data come from simulation with known ground truth inverted by the same kinetic form, so the study verifies pipeline self-consistency and the identifiability boundary, not real parameters.

Citations

• Physics-informed machine learning
• Physics-informed neural networks (PINNs) for fluid mechanics: A review
• Physics-informed neural networks (PINNs) for fluid mechanics: a review
• Thermodynamically consistent physics-informed neural networks for hyperbolic systems
• ChemNODE: A Neural Ordinary Differential Equations Approach for Chemical\n Kinetics Solvers
• When and why PINNs fail to train: A neural tangent kernel perspective
• When and why PINNs fail to train: A neural tangent kernel perspective
• hp-VPINNs: Variational physics-informed neural networks with domain decomposition
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• Universal Differential Equations for Scientific Machine Learning
• DeepXDE: A Deep Learning Library for Solving Differential Equations
• fPINNs: Fractional Physics-Informed Neural Networks
• Neural Ordinary Differential Equations
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial\n Differential Equations
• Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
• Sigmoid-weighted linear units for neural network function approximation in reinforcement learning
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Sloppiness and Emergent Theories in Physics, Biology, and Beyond
• Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood
• A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code
• THE ADSORPTION OF GASES ON PLANE SURFACES OF GLASS, MICA AND PLATINUM.