Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors

2025-07-07

AI Summary

This work addresses the low efficiency, compact-model dependency, and poor generalizability of manual extraction of physical parameters—such as carrier mobility, Schottky barrier height, and defect distribution—in two-dimensional (2D) transistors. We propose a physics-informed deep learning framework that integrates physical priors with TCAD co-simulation for pretraining, augmented by targeted data enhancement strategies. Using only 500 synthetic TCAD samples, our method achieves high-accuracy parameter inversion—reducing sample requirements by over 40× compared to state-of-the-art approaches. It supports complex device geometries and self-consistent transport modeling, attaining a median R² of 0.99 on experimental monolayer WS₂ transistor data. Crucially, it simultaneously inverts 35 distinct physical parameters with strong generalizability and scalability. This establishes a new paradigm for automated modeling and process optimization of 2D semiconductor devices.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We present a deep learning approach to extract physical parameters (e.g., mobility, Schottky contact barrier height, defect profiles) of two-dimensional (2D) transistors from electrical measurements, enabling automated parameter extraction and technology computer-aided design (TCAD) fitting. To facilitate this task, we implement a simple data augmentation and pre-training approach by training a secondary neural network to approximate a physics-based device simulator. This method enables high-quality fits after training the neural network on electrical data generated from physics-based simulations of ~500 devices, a factor >40$ imes$ fewer than other recent efforts. Consequently, fitting can be achieved by training on physically rigorous TCAD models, including complex geometry, self-consistent transport, and electrostatic effects, and is not limited to computationally inexpensive compact models. We apply our approach to reverse-engineer key parameters from experimental monolayer WS$_2$ transistors, achieving a median coefficient of determination ($R^2$) = 0.99 when fitting measured electrical data. We also demonstrate that this approach generalizes and scales well by reverse-engineering electrical data on high-electron-mobility transistors while fitting 35 parameters simultaneously. To facilitate future research on deep learning approaches for inverse transistor design, we have published our code and sample data sets online.

Problem

• Automate parameter extraction from 2D transistor measurements
• Reduce training data needs for deep learning models
• Enable complex TCAD model fitting with neural networks

Innovation

• Deep learning automates 2D transistor parameter extraction
• Data augmentation enhances training with physics simulations
• TCAD models enable complex geometry and transport fitting