Process-Technology Co-optimization for 2D-FETs
Abstract
We present the first experimental machine learning (ML)-enabled Process-Technology Co-Optimization (PTCO) framework for optimizing 2D transition metal dichalcogenide (TMD) FET fabrication directly from statistically meaningful experimental data rather than pure simulation data. We first introduce a transition voltage metric, VTrans, to quantify the gate voltage required for off-to-on switching and reveal its direct correlation with subthreshold swing (SS), highlighting an overlooked switching characteristic that governs both off-state and on-state performance. By integrating automated metric extraction, multi-objective recipe ranking, and predictive modeling, our framework uncovers hidden process-performance correlations and predicts the performance of unexplored fabrication recipes from limited experimental data. Experimental validation shows close agreement with ML predictions, thus demonstrating the framework's ability to efficiently guide gate stack optimization through iterative experimental feedback.
Related
- Fast On-Chip Thermometry with TiN Kinetic Inductance Resonators in 22 nm Process Technology
- Data-driven surface figure analysis and process optimization for full-aperture continuous polishing based on processing data
- Multiscale modelling of nanoscaled FETs based on 2D ferroelectric materials
- Optically Coupled Noise Spectroscopy Quantifies Defect Passivation in Monolayer MoS2 FETs
- Quantum-echo Markov process for combinatorial optimization
BibTeX
@misc{yang2026processtechnology,
title = {{Process-Technology Co-optimization for 2D-FETs}},
author = {Shao-Heng Yang and Jainil Dharmil Shah and Mayukh Das and Yuanqiu Tan and Hao-Yu Lan and Hsing-Chien Chien and Himani Jawa and Shalini Tripathi and Marco Antonio Villena and Xiangyu Wu and Daire Cott and Kaustav Banerjee and Pierre Morin and César Javier Lockhart de la Rosa and Gaurav Thareja and Dennis Lin and Joerg Appenzeller and Zhihong Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00722},
eprint = {2609.00722},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00722},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Process-Technology Co-optimization for 2D-FETs
AU - Shao-Heng Yang
AU - Jainil Dharmil Shah
AU - Mayukh Das
AU - Yuanqiu Tan
AU - Hao-Yu Lan
AU - Hsing-Chien Chien
AU - Himani Jawa
AU - Shalini Tripathi
AU - Marco Antonio Villena
AU - Xiangyu Wu
AU - Daire Cott
AU - Kaustav Banerjee
AU - Pierre Morin
AU - César Javier Lockhart de la Rosa
AU - Gaurav Thareja
AU - Dennis Lin
AU - Joerg Appenzeller
AU - Zhihong Chen
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00722
UR - https://arxiv.org/abs/2609.00722
AB - We present the first experimental machine learning (ML)-enabled Process-Technology Co-Optimization (PTCO) framework for optimizing 2D transition metal dichalcogenide (TMD) FET fabrication directly from statistically meaningful experimental data rather than pure simulation data. We first introduce a transition voltage metric, VTrans, to quantify the gate voltage required for off-to-on switching and reveal its direct correlation with subthreshold swing (SS), highlighting an overlooked switching characteristic that governs both off-state and on-state performance. By integrating automated metric extraction, multi-objective recipe ranking, and predictive modeling, our framework uncovers hidden process-performance correlations and predicts the performance of unexplored fabrication recipes from limited experimental data. Experimental validation shows close agreement with ML predictions, thus demonstrating the framework's ability to efficiently guide gate stack optimization through iterative experimental feedback.
ER -