Device-Scale Atomistic Simulations of Heat Transport in Advanced Field-Effect Transistors

TL;DR

This paper introduces NEP-FET, a machine learning framework for atomistic simulations of heat transport in advanced transistors, enabling high-fidelity, device-scale thermal analysis with rapid throughput.

Contribution

The paper presents NEP-FET, a novel machine-learned simulation framework that combines quantum accuracy with device-scale modeling for heat transport in transistors.

Findings

Significant temperature distribution differences between transistor architectures.

NEP-FET accurately predicts temperature fields and heat flux at the atomistic level.

Framework enables rapid thermal metric estimation for device design.

Abstract

Self-heating in next-generation, high-power-density field-effect transistor limits performance and complicates fabrication. Here, we introduce NEP-FET, a machine-learned framework for device-scale heat transport simulations of field-effect transistors. Built upon the neuroevolution potential, the model extends a subset of the OMat24 dataset through an active-learning workflow to generate a chemically diverse, interface-rich reference set. Coupled with the FETMOD structure generator module, NEP-FET can simulate realistic field-effect transistor geometries at sub-micrometer scales containing millions of atoms, and delivers atomistic predictions of temperature fields, per-atom heat flux, and thermal stress in device structures with high fidelity. This framework enables rapid estimation of device-level metrics, including heat-flux density and effective thermal conductivity. Our results reveal pronounced differences in temperature distribution between fin-type and gate-all-around transistor architectures. The framework closes a key gap in multiscale device modeling by combining near-quantum-mechanical accuracy with device-scale throughput, providing a systematic route to explore heat transport and thermo-mechanical coupling in advanced transistors.