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

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.

References in corpus (11)

• Nearsightedness of Electronic Matter
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• On scientific understanding with artificial intelligence
• An Accurate and Transferable Machine Learning Potential for Carbon
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states
• Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning
• Towards DMC accuracy across chemical space with scalable $\Delta$-QML
• Modeling electronic response properties with an explicit-electron machine learning potential
• Practical error bounds for properties in plane-wave electronic structure calculations

Cited by in corpus (19)

• Probing out-of-distribution generalization in machine learning for materials
• El Agente: An Autonomous Agent for Quantum Chemistry
• A reactive neural network framework for water-loaded acidic zeolites
• Multimodal Foundation Models for Material Property Prediction and Discovery
• Why neural functionals suit statistical mechanics
• Machine Learning-Guided Screening of Advantageous Solvents for Solid Polymer Electrolytes in Lithium Metal Batteries
• Reducing Training Data Needs with Minimal Multilevel Machine Learning (M3L)
• Improved decision making with similarity based machine learning: Applications in chemistry
• Machine learning based nonlocal kinetic energy density functional for simple metals and alloys
• Decoding Drug Discovery: Exploring A-to-Z In silico Methods for Beginners
• Multi-channel machine learning based nonlocal kinetic energy density functional for semiconductors
• Orbital-Free Quasi-Density Functional Theory
• Evolutionary Monte Carlo of QM properties in chemical space: Electrolyte design
• Ensemble Generalization of the Perdew-Zunger Self-Interaction Correction: a Way Out of Multiple Minima and Symmetry Breaking
• Combining Hammett $\sigma$ constants for $\Delta$-machine learning and catalyst discovery
• All-in-one foundational models learning across quantum chemical levels
• Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules
• Metadensity functional learning for classical fluids: Regularizing with pair correlations
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials