aiqbench analysis
This research applies deep learning techniques to automate the extraction of physical parameters from 2D transistor electrical measurements, significantly reducing the data required for training compared to previous methods. By using a neural network to approximate complex physics-based simulators, the approach achieves high-accuracy fitting for diverse device geometries and materials, including monolayer WS₂ transistors. The work demonstrates a scalable framework for inverse design in semiconductor technology computer-aided design (TCAD), with code and datasets made available for further development.
Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors
arXiv:2507.05134v2 Announce Type: replace 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$\times$ 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.
Authors:Robert K. A. Bennett, Jan-Lucas Uslu, Harmon F. Gault, Asir Intisar Khan, Lauren Hoang, Tara Peña, Kathryn Neilson, Young Suh Song, Zhepeng Zhang, Andrew J. Mannix, Eric Pop
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$\times$ 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.
Main text + supplementary information. Updated to be aligned with the recently published version of the manuscript
Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Applied Physics (physics.app-ph)
arXiv:2507.05134 [cs.LG]
(or arXiv:2507.05134v2 [cs.LG] for this version)
Bennett, R.K.A., et al. Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors. Research (9) 2026
https://doi.org/10.34133/research.1103 DOI(s) linking to related resources
Full text under the publisher's open licence · 275 words
Related coverage
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · Oct 8, 2026
Sandia Labs maps a path to faster spin qubit tuning
Quantum Zeitgeist · Sep 16, 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026
News
Quantum Computing Report · Jun 7, 2026