Physics-Constrained Adaptive Neural Networks Enable Real-Time Semiconductor Manufacturing Optimization with Minimal Training Data

TL;DR

This paper introduces a physics-constrained adaptive neural network framework that significantly reduces training data needs and computational cost for real-time EUV lithography optimization, achieving high precision with minimal data.

Contribution

The work presents a novel physics-constrained adaptive learning method that calibrates electromagnetic models and minimizes pattern errors, enabling efficient, generalizable semiconductor manufacturing optimization.

Findings

Achieves sub-nanometer Edge Placement Error with only 50 training samples per pattern.

Improves accuracy by 69.9% over CNN baselines without physics constraints.

Reduces training data requirements by 90% compared to pattern-specific CNNs.

Abstract

The semiconductor industry faces a computational crisis in extreme ultraviolet (EUV) lithography optimization, where traditional methods consume billions of CPU hours while failing to achieve sub-nanometer precision. We present a physics-constrained adaptive learning framework that automatically calibrates electromagnetic approximations through learnable parameters $\boldsymbol{\theta} = \{\theta_d, \theta_a, \theta_b, \theta_p, \theta_c\}$ while simultaneously minimizing Edge Placement Error (EPE) between simulated aerial images and target photomasks. The framework integrates differentiable modules for Fresnel diffraction, material absorption, optical point spread function blur, phase-shift effects, and contrast modulation with direct geometric pattern matching objectives, enabling cross-geometry generalization with minimal training data. Through physics-constrained learning on 15 representative patterns spanning current production to future research nodes, we demonstrate consistent sub-nanometer EPE performance (0.664-2.536 nm range) using only 50 training samples per pattern. Adaptive physics learning achieves an average improvement of 69.9\% over CNN baselines without physics constraints, with a significant inference speedup over rigorous electromagnetic solvers after training completion. This approach requires 90\% fewer training samples through cross-geometry generalization compared to pattern-specific CNN training approaches. This work establishes physics-constrained adaptive learning as a foundational methodology for real-time semiconductor manufacturing optimization, addressing the critical gap between academic physics-informed neural networks and industrial deployment requirements through joint physics calibration and manufacturing precision objectives.