Efficient first principles based modeling via machine learning: from simple representations to high entropy materials

Abstract

High-entropy materials (HEMs) have recently emerged as a significant category of materials, offering highly tunable properties. However, the scarcity of HEM data in existing density functional theory (DFT) databases, primarily due to computational expense, hinders the development of effective modeling strategies for computational materials discovery. In this study, we introduce an open DFT dataset of alloys and employ machine learning (ML) methods to investigate the material representations needed for HEM modeling. Utilizing high-throughput DFT calculations, we generate a comprehensive dataset of 84k structures, encompassing both ordered and disordered alloys across a spectrum of up to seven components and the entire compositional range. We apply descriptor-based models and graph neural networks to assess how material information is captured across diverse chemical-structural representations. We first evaluate the in-distribution performance of ML models to confirm their predictive accuracy. Subsequently, we demonstrate the capability of ML models to generalize between ordered and disordered structures, between low-order and high-order alloys, and between equimolar and non-equimolar compositions. Our findings suggest that ML models can generalize from cost-effective calculations of simpler systems to more complex scenarios. Additionally, we discuss the influence of dataset size and reveal that the information loss associated with the use of unrelaxed structures could significantly degrade the generalization performance. Overall, this research sheds light on several critical aspects of HEM modeling and offers insights for data-driven atomistic modeling of HEMs.

arXiv commentDFT dataset available at https://doi.org/10.5281/zenodo.10854500

References in corpus (17)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• The Alloy Theoretic Automated Toolkit: A User Guide
• AFLOW: An automatic framework for high-throughput materials discovery
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• High-entropy high-hardness metal carbides discovered by entropy descriptors
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• A map of single-phase high-entropy alloys
• A critical examination of robustness and generalizability of machine learning prediction of materials properties
• The role of decomposition reactions in assessing first-principles predictions of solid stability
• On the redundancy in large material datasets: efficient and robust learning with less data
• Efficient machine-learning model for fast assessment of elastic properties of high-entropy alloys
• Calibrating DFT formation enthalpy calculations by multi-fidelity machine learning
• Magnetochemical effects on phase stability and vacancy formation in fcc Fe-Ni alloys

Cited by in corpus (3)

• Probing out-of-distribution generalization in machine learning for materials
• LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction
• SPEA -- an analytical thermodynamic model for defect phase diagram