Accurate large-scale simulations of siliceous zeolites by neural network potentials

Abstract

The computational discovery and design of zeolites is a crucial part of the chemical industry. Finding highly accurate while computationally feasible protocol for identification of hypothetical zeolites that could be targeted experimentally is a great challenge. To tackle the challenge, we trained neural network potentials (NNP) with the SchNet architecture on a structurally diverse database of density functional theory (DFT) data. This database was iteratively extended by active learning to cover not only low-energy equilibrium configurations but also high-energy transition states. We demonstrate that the resulting reactive NNPs retain the accuracy of the DFT reference for thermodynamic stabilities, vibrational properties, and reactive and non-reactive phase transformations. The novel NNPs outperforms specialized, analytical force fields for silica, such as ReaxFF, by order(s) of magnitude in accuracy, while speeding up the calculations in comparison to DFT by at least three orders of magnitude. As a showcase, we screened an existing zeolite database containing 330 thousand structures and revealed more than 20 thousand additional hypothetical frameworks in the thermodynamically accessible range of zeolite synthesis. Hence, our NNPs are expected to be essential for future high-throughput studies on the structure and reactivity of hypothetical and existing zeolites.

arXiv commentThis version of the article has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available on line at: http://dx.doi.org/10.1038/s41524-022-00865-w

References in corpus (21)

• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Comparing molecules and solids across structural and alchemical space
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Hierarchical modeling of molecular energies using a deep neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• DynaPhoPy: A code for extracting phonon quasiparticles from molecular dynamics simulations
• Committee neural network potentials control generalization errors and enable active learning
• Benchmark tests of a strongly constrained semilocal functional with a long-range dispersion correction
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Phonon Quasi-Particles and Anharmonic Free Energy in Complex Systems
• Graph similarity drives zeolite diffusionless transformations and intergrowth
• Amorphization induced by pressure: results for zeolites and general implications
• Structural stability and lattice dynamics of SiO2 cristobalite
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• A New Kind of Atlas of Zeolite Building Blocks
• Machine Learning Forcefield for Silicate Glasses

Cited by in corpus (2)

• A reactive neural network framework for water-loaded acidic zeolites
• Inorganic synthesis-structure maps in zeolites with machine learning and crystallographic distances