Teaching oxidation states to neural networks

Abstract

While the accurate description of redox reactions remains a challenge for first-principles calculations, it has been shown that extended Hubbard functionals (DFT+U+V) can provide a reliable approach, mitigating self-interaction errors, in materials with strongly localized d or f electrons. Here, we first show that DFT+U+V molecular dynamics is capable to follow the adiabatic evolution of oxidation states over time, using representative Li-ion cathode materials. In turn, this allows to develop redox-aware machine-learned potentials. We show that considering atoms with different oxidation states (as accurately predicted by DFT+U+V) as distinct species in the training leads to potentials that are able to identify the correct ground state and pattern of oxidation states for redox elements present. This can be achieved, e.g., through a systematic combinatorial search for the lowest energy configuration or with stochastic methods. This brings the advantages of machine-learned potentials to key technological applications (e.g., rechargeable batteries), which require an accurate description of the evolution of redox states.

References in corpus (29)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Canonical sampling through velocity-rescaling
• Restoring the density-gradient expansion for exchange in solids and surfaces
• Generalized gradient approximation for solids and their surfaces
• Advanced capabilities for materials modelling with Quantum ESPRESSO
• A linear response approach to the calculation of the effective interaction parameters in the LDA+U method
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Pseudopotentials for high-throughput DFT calculations
• Density functional theory in transition-metal chemistry: a self-consistent Hubbard U approach
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Hubbard parameters from density-functional perturbation theory
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• Regularized SCAN functional
• The discontinuous nature of the exchange-correlation functional -- critical for strongly correlated systems
• Self-consistent Hubbard parameters from density-functional perturbation theory in the ultrasoft and projector-augmented wave formulations
• Extended DFT+U+V method with on-site and inter-site electronic interactions
• Evaluating transition-metal oxides within DFT-SCAN and SCAN+U frameworks for solar thermochemical applications
• How to verify the precision of density-functional-theory implementations via reproducible and universal workflows
• Parameter-free hybrid functional based on an extended Hubbard model: DFT+U+V
• Realistic, quantitative descriptions of electron-transfer reactions: diabatic free-energy surfaces from first-principles molecular dynamics
• Rigorous definition of oxidation states of ions in solids
• Energetics and cathode voltages of LiMPO${}_4$ olivines (M = Fe, Mn) from extended Hubbard functionals
• Efficient First-Principles Approach with a Pseudohybrid Density Functional for Extended Hubbard Interactions
• Pulay forces in density-functional theory with extended Hubbard functionals: From nonorthogonalized to orthogonalized manifolds
• Topological quantisation and gauge invariance of charge transport in liquid insulators
• Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
• Data-driven Approach to Parameterize SCAN+U for an Accurate Description of 3d Transition Metal Oxide Thermochemistry