Band gap prediction for large organic crystal structures with machine learning

Abstract

Machine-learning models are capable of capturing the structure-property relationship from a dataset of computationally demanding ab initio calculations. Over the past two years, the Organic Materials Database (OMDB) has hosted a growing number of calculated electronic properties of previously synthesized organic crystal structures. The complexity of the organic crystals contained within the OMDB, which have on average 82 atoms per unit cell, makes this database a challenging platform for machine learning applications. In this paper, the focus is on predicting the band gap which represents one of the basic properties of a crystalline materials. With this aim, a consistent dataset of 12 500 crystal structures and their corresponding DFT band gap are released, freely available for download at https://omdb.mathub.io/dataset. An ensemble of two state-of-the-art models reach a mean absolute error (MAE) of 0.388 eV, which corresponds to a percentage error of 13% for an average band gap of 3.05 eV. Finally, the trained models are employed to predict the band gap for 260 092 materials contained within the Crystallography Open Database (COD) and made available online so that the predictions can be obtained for any arbitrary crystal structure uploaded by a user.

arXiv comment10 pages, 6 figures

References in corpus (21)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Spin Liquid State in an Organic Mott Insulator with Triangular Lattice
• Comparing molecules and solids across structural and alchemical space
• By-passing the Kohn-Sham equations with machine learning
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Machine learning modeling of superconducting critical temperature
• Spin qubits with electrically gated polyoxometalate molecules
• U(1) Gauge Theory of the Hubbard Model : Spin Liquid States and Possible Application to k-(BEDT-TTF)_2 Cu_2 (CN)_3
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Hierarchical modeling of molecular energies using a deep neural network
• Atom2Vec: learning atoms for materials discovery
• Direct Observation of Quantum Coherence in Single-Molecule Magnets
• Atom-Density Representations for Machine Learning
• Quantum Spin Liquids Unveil the Genuine Mott State
• Towards Novel Organic High-$T_{\mathrm{c}}$ Superconductors: Data Mining using Density of States Similarity Search
• Online Search Tool for Graphical Patterns in Electronic Band Structures

Cited by in corpus (12)

• Database of 2D hybrid perovskite materials: open-access collection of crystal structures, band gaps and atomic partial charges predicted by machine learning
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks
• Machine learning of phase transitions in nonlinear polariton lattices
• Visualising energy landscapes through manifold learning
• Machine learning band gaps from the electron density
• Gallium-Boron-Phosphide (GaBP${}_2$): A New III-V Semiconductor for photovoltaics
• Identification of strongly interacting organic semimetals
• Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
• Machine learning frontier orbital energies of nanodiamonds
• Spin wave excitations of magnetic metalorganic materials