Towards self-driving laboratories: The central role of density functional theory in the AI age

TL;DR

This paper reviews how density functional theory (DFT) underpins machine learning advancements in chemical and materials sciences, enabling efficient, accurate, and scalable models that facilitate autonomous experimental planning in self-driving laboratories.

Contribution

It highlights recent progress in ML models relying on DFT data, emphasizing their potential for routine use in autonomous chemical and materials research.

Findings

DFT-based ML models exhibit high efficiency, accuracy, scalability, and transferability.

Recent developments suggest feasible integration into self-driving laboratory workflows.

DFT remains central to advancing AI-driven experimental design in chemistry and materials science.

Abstract

Density functional theory (DFT) plays a pivotal role for the chemical and materials science due to its relatively high predictive power, applicability, versatility and computational efficiency. We review recent progress in machine learning model developments which has relied heavily on density functional theory for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in some broader context for the chemical and materials sciences. Resulting in DFT based machine learning models with high efficiency, accuracy, scalability, and transferability (EAST), recent progress indicates probable ways for the routine use of successful experimental planning software within self-driving laboratories.