Database-driven High-Throughput Calculations and Machine Learning Models for Materials Design

TL;DR

This paper reviews how high-throughput ab-initio calculations combined with machine learning models are advancing materials design, focusing on bulk materials and emphasizing automated data generation and predictive modeling.

Contribution

It provides a comprehensive overview of computational methods, tools, and machine learning techniques used for automated database-driven materials discovery.

Findings

High-throughput calculations enable large data sets for materials prediction

Machine learning models can predict stability and properties of bulk materials

Automated computational workflows improve efficiency and reliability

Abstract

This paper reviews past and ongoing efforts in using high-throughput ab-inito calculations in combination with machine learning models for materials design. The primary focus is on bulk materials, i.e., materials with fixed, ordered, crystal structures, although the methods naturally extend into more complicated configurations. Efficient and robust computational methods, computational power, and reliable methods for automated database-driven high-throughput computation are combined to produce high-quality data sets. This data can be used to train machine learning models for predicting the stability of bulk materials and their properties. The underlying computational methods and the tools for automated calculations are discussed in some detail. Various machine learning models and, in particular, descriptors for general use in materials design are also covered.