InterMat: Accelerating Band Offset Prediction in Semiconductor Interfaces with DFT and Deep Learning

Abstract

We introduce a computational framework (InterMat) to predict band offsets of semiconductor interfaces using density functional theory (DFT) and graph neural networks (GNN). As a first step, we benchmark OptB88vdW generalized gradient approximation (GGA) work functions and electron affinities for surfaces against experimental data with accuracies of 0.29 eV and 0.39 eV, respectively. Similarly, we evaluate band offset values using independent unit (IU) and alternate slab junction (ASJ) models leading to accuracies of 0.45 eV and 0.22 eV, respectively. We use bulk band structure calculations with the TBmBJ meta-GGA functional to correct for band gap underestimation when predicting conduction band properties. During ASJ structure generation, we use Zur algorithm along with a unified GNN force-field to tackle the conformation challenges of interface design. At present, we have 607 surface work functions calculated with DFT, from which we can compute 183921 IU band offsets as well as 593 directly calculated ASJ band offsets. Finally, as the space of all possible heterojunctions is too large to simulate with DFT, we develop generalized GNN models to quickly predict bulk band edges with an accuracy of 0.26 eV. We show how these models can be used to predict relevant quantities including ionization potentials, electron affinities, and IU-based band offsets. We establish simple rules using the above models to pre-screen potential semiconductor devices from a vast pool of nearly 1.4 trillion candidate interfaces. InterMat is available at website: https://github.com/usnistgov/intermat

References in corpus (20)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• Convergence and machine learning predictions of Monkhorst-Pack k-points and plane-wave cut-off in high-throughput DFT calculations
• Computational screening of high-performance optoelectronic materials using OptB88vdW and TB-mBJ formalisms
• MPInterfaces: A Materials Project based Python Tool for High-Throughput Computational Screening of Interfacial Systems
• Unified Graph Neural Network Force-field for the Periodic Table
• Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties
• Band gap and band alignment prediction of nitride based semiconductors using machine learning
• Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning
• High-Throughput DFT-Based Discovery of Next Generation Two-Dimensional (2D) Superconductors
• Thermal boundary resistance at Si/Ge interfaces determined by approach-to-equilibrium molecular dynamics simulations
• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• Efficient Computational Design of 2D van der Waals Heterostructures: Band-Alignment, Lattice-Mismatch, Web-app Generation and Machine-learning
• ChemNLP: A Natural Language Processing based Library for Materials Chemistry Text Data
• Recent progress in the JARVIS infrastructure for next-generation data-driven materials design
• A Deep-learning Model for Fast Prediction of Vacancy Formation in Diverse Materials
• Efficient and improved prediction of the band offsets at semiconductor heterojunctions from meta-GGA density functionals
• AtomVision: A machine vision library for atomistic images
• AtomGPT: Atomistic Generative Pre-trained Transformer for Forward and Inverse Materials Design

Cited by in corpus (4)

• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Structure Prediction of Ionic Epitaxial Interfaces with Ogre Demonstrated for Colloidal Heterostructures of Lead Halide Perovskites
• The JARVIS Infrastructure is All You Need for Materials Design
• RAFFLE: Active learning accelerated interface structure prediction