Fully Convolutional Generative Machine Learning Method for Accelerating Non-Equilibrium Green's Function Simulations

Preslav Aleksandrov*, Ali Rezaei, Nikolas Xeni, Tapas Dutta, Asen Asenov, Vihar Georgiev

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This work describes a novel simulation approach that combines machine learning and device modeling simulations. The device simulations are based on the quantum mechanical non-equilibrium Green's function (NEGF) approach and the machine learning method is an extension to a convolutional generative network. We have named our new simulation approach ML-NEGF and we have implemented it in our in-house simulator called NESS (nano-electronics simulations software). The reported results demonstrate the improved convergence speed of the ML-NEGF method in comparison to the 'standard' NEGF approach. The trained ML model effectively learns the underlying physics of nano-sheet transistor behaviour, resulting in faster convergence of the coupled Poisson-NEGF simulations. Quantitatively, our ML-NEGF approach achieves an average convergence acceleration of 60%, substantially reducing the computational time while maintaining the same accuracy.

Original languageEnglish
Title of host publication2023 International Conference on Simulation of Semiconductor Processes and Devices, SISPAD 2023
PublisherIEEE
Pages169-172
Number of pages4
ISBN (Electronic)9784863488038
DOIs
Publication statusPublished - 20 Nov 2023
Event2023 International Conference on Simulation of Semiconductor Processes and Devices, SISPAD 2023 - Kobe, Japan
Duration: 27 Sept 202329 Sept 2023

Publication series

NameInternational Conference on Simulation of Semiconductor Processes and Devices, SISPAD

Conference

Conference2023 International Conference on Simulation of Semiconductor Processes and Devices, SISPAD 2023
Country/TerritoryJapan
CityKobe
Period27/09/2329/09/23

Keywords / Materials (for Non-textual outputs)

  • autoencoder
  • device simulations and modeling
  • machine learning
  • nanowires
  • neural network
  • non-equilibrium Green's function (NEGF)
  • TCAD device modeling

Fingerprint

Dive into the research topics of 'Fully Convolutional Generative Machine Learning Method for Accelerating Non-Equilibrium Green's Function Simulations'. Together they form a unique fingerprint.

Cite this