Machine learning-guided quantum chaos engineering in MoS 2 transistors
Physica Scripta · 08.05.2026 · 101 (18) · 186006
DOI: 10.1088/1402-4896/ae6486 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 07.05.2026. Verfasst von S Mehrmanesh und 1 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben.
Abstract (Originalsprache)
The design of high-performance, stable transistors based on two-dimensional materials such as molybdenum disulfide ( MoS 2 ) demands a thorough understanding of how disorder, electrostatic gating, and thermal effects shape electron transport. To move beyond conventional simulation approaches, this study introduces a novel framework that combines quantum chaos theory with machine learning to model and predict the behavior of MoS 2 field-effect transistors. Using the statistical distribution of quantum energy levels-quantified by the Brody parameter-we diagnose transitions between insulating (localized) and metallic (chaotic) states. Our findings reveal that tungsten impurity concentration, gate voltage, and temperature serve as interdependent control parameters for quantum chaos, enabling deliberate tuning of the channel’s metal-insulator transition. In addition, a trained multilayer perceptron accurately predicts the quantum chaotic signature, providing a fast and reliable surrogate for device simulations. This work establishes a new paradigm where machine learning serves as a high-fidelity surrogate for quantum chaos diagnostics, enabling rapid exploration of multidimensional design spaces and inverse engineering of 2D transistors based on fundamental quantum-state criteria rather than empirical performance metrics.
Zitieren
APA
Mehrmanesh, S., & Behnia, S. (2026). Machine learning-guided quantum chaos engineering in MoS 2 transistors. Physica Scripta, 101(18), 186006. https://doi.org/10.1088/1402-4896/ae6486
Vancouver
Mehrmanesh S, Behnia S. Machine learning-guided quantum chaos engineering in MoS 2 transistors. Physica Scripta. 2026;101(18):186006. doi:10.1088/1402-4896/ae6486
BibTeX
@article{Mehrmanesh2026,
author = {Mehrmanesh, S and Behnia, S},
title = {Machine learning-guided quantum chaos engineering in MoS 2 transistors},
journal = {Physica Scripta},
year = {2026},
volume = {101},
number = {18},
pages = {186006},
doi = {10.1088/1402-4896/ae6486}
}
EUVIMED