Dissertation Machine Learning in Materials Science -- A case study in Carbon Nanotube field effect transistors

TL;DR

This thesis investigates the application of various machine learning techniques to predict and analyze the performance and properties of carbon nanotube field effect transistors, advancing materials science research.

Contribution

It introduces the use of neural networks, simulation-based inference, and generative flow networks for modeling and generating CNTFETs data, which is novel in this context.

Findings

Improved prediction accuracy of CNTFET performance

Enhanced understanding of CNT network conductivity

Generated CNTFET processing data for targeted performance

Abstract

In this thesis, I explored the use of several machine learning techniques, including neural networks, simulation-based inference, and generative flow networks, on predicting CNTFETs performance, probing the conductivity properties of CNT network, and generating CNTFETs processing information for target performance.