Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks

Abstract

High-throughput computational screening has emerged as a critical component of materials discovery. Direct density functional theory (DFT) simulation of inorganic materials and molecular transition metal complexes is often used to describe subtle trends in inorganic bonding and spin-state ordering, but these calculations are computationally costly and properties are sensitive to the exchange-correlation functional employed. To begin to overcome these challenges, we trained artificial neural networks (ANNs) to predict quantum-mechanically-derived properties, including spin-state ordering, sensitivity to Hartree-Fock exchange, and spin- state specific bond lengths in transition metal complexes. Our ANN is trained on a small set of inorganic-chemistry-appropriate empirical inputs that are both maximally transferable and do not require precise three-dimensional structural information for prediction. Using these descriptors, our ANN predicts spin-state splittings of single-site transition metal complexes (i.e., Cr-Ni) at arbitrary amounts of Hartree-Fock exchange to within 3 kcal/mol accuracy of DFT calculations. Our exchange-sensitivity ANN enables improved predictions on a diverse test set of experimentally-characterized transition metal complexes by extrapolation from semi-local DFT to hybrid DFT. The ANN also outperforms other machine learning models (i.e., support vector regression and kernel ridge regression), demonstrating particularly improved performance in transferability, as measured by prediction errors on the diverse test set. We establish the value of new uncertainty quantification tools to estimate ANN prediction uncertainty in computational chemistry, and we provide additional heuristics for identification of when a compound of interest is likely to be poorly predicted by the ANN.

26 pages of text, 13 figures, 4 tables

References in corpus (8)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accelerated materials property predictions and design using motif-based fingerprints
• The Many-Body Expansion Combined with Neural Networks
• Towards quantifying the role of exact exchange in predictions of transition metal complex properties
• Systematic Error Estimation for Chemical Reaction Energies
• Where Does the Density Localize? Convergent Behavior for Global Hybrids, Range Separation, and DFT+U
• Comparing the Accuracy of High-Dimensional Neural Network Potentials and the Systematic Molecular Fragmentation Method: A Benchmark Study for all-trans Alkanes

Cited by in corpus (17)

• Machine learning for electronically excited states of molecules
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• Message-passing neural networks for high-throughput polymer screening
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Machine Learning Configuration Interaction
• High-Dimensional Neural Network Potentials for Magnetic Systems Using Spin-Dependent Atom-Centered Symmetry Functions
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Reliable estimation of prediction uncertainty for physico-chemical property models
• Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery
• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states
• Machine learning configuration interaction for ab initio potential energy curves
• Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
• Machine learning the computational cost of quantum chemistry
• Spin-free formulation of the multireference driven similarity renormalization group: A benchmark study of first-row diatomic molecules and spin-crossover energetics
• Representations and Strategies for Transferable Machine Learning Models in Chemical Discovery
• Quantum chemical roots of machine-learning molecular similarity descriptors