Catalytic materials and chemistry development using a synergistic combination of machine learning and ab initio methods

Abstract First principles-based molecular modelling plays a crucial role in the development of novel catalytic materials and in the investigation of catalytic chemical reactions. However, the computational cost and/or the accuracy of these models remains a bottleneck in carrying out these simulations for complex or large scale systems, as in the case of catalysis. Over the past two decades, machine learning (ML) has made an impact in the field of computational catalysis. Modern-day researchers have started using machine learning-based data-driven techniques to overcome the limitations of these molecular simulations. In this review, we summarize the recent progress in the utilization of ML algorithms to assist molecular simulations, followed by its applications in the field of catalysis. Furthermore, we provide our perspective on promising avenues for research in the future regarding the incorporation of ML in molecular simulations in catalysis.

• Publication year

  2020

• Venue

  Computational Materials Science

• Publication date

  2020-03-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1016/j.commatsci.2019.109474
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Machine learning for renewable energy materials

  2019cited by this paper
• Beyond Scaling Relations for the Description of Catalytic Materials

  2019cited by this paper
• Robust and synthesizable photocatalysts for CO2 reduction: a data-driven materials discovery

  2019cited by this paper
• From DFT to machine learning: recent approaches to materials science–a review

  2019cited by this paper
• Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning

  2019cited by this paper
• Predicting synthesizability

  2019cited by this paper
• Convolutional Neural Network of Atomic Surface structures to Predict Binding Energies For High-throughput Screening of Catalysts.

  2019cited by this paper
• Metadynamics

  2019cited by this paper
• Unfolding adsorption on metal nanoparticles: Connecting stability with catalysis

  2019cited by this paper
• Cutting Materials in Half: A Graph Theory Approach for Generating Crystal Surfaces and Its Prediction of 2D Zeolites

  2018cited by this paper
• Machine learning for molecular and materials science

  2018cited by this paper
• Machine learning for heterogeneous catalyst design and discovery

  2018cited by this paper
• Machine learning in catalysis

  2018cited by this paper
• Transferable Neural Networks for Enhanced Sampling of Protein Dynamics.

  2018cited by this paper
• Extracting Knowledge from Data through Catalysis Informatics

  2018cited by this paper
• Recent progress in nanostructured magnetic framework composites (MFCs): Synthesis and applications

  2018cited by this paper
• Hydrothermal synthesis of NH2-UiO-66 and its application for adsorptive removal of dye

  2018cited by this paper
• Using Machine Learning To Predict Suitable Conditions for Organic Reactions

  2018cited by this paper
• Machine Learning and Energy Minimization Approaches for Crystal Structure Predictions: A Review and New Horizons

  2018cited by this paper
• Recruiting machine learning methods for molecular simulations of proteins

  2018cited by this paper
• Towards exact molecular dynamics simulations with machine-learned force fields

  2018cited by this paper
• Accelerating the discovery of materials for clean energy in the era of smart automation

  2018cited by this paper
• Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution

  2018cited by this paper
• Machine Learning in Computer-Aided Synthesis Planning.

  2018cited by this paper
• Network analysis of synthesizable materials discovery

  2018cited by this paper
• SCScore: Synthetic Complexity Learned from a Reaction Corpus

  2018cited by this paper
• Quantum Machine Learning in Chemical Compound Space.

  2018cited by this paper
• Artificial neural network analysis of the catalytic efficiency of platinum nanoparticles

  2017cited by this paper
• Transfer Learning from Markov models leads to efficient sampling of related systems

  2017cited by this paper
• tICA-Metadynamics: Accelerating Metadynamics by Using Kinetically Selected Collective Variables.

  2017cited by this paper
• Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods

  2017cited by this paper
• Deep learning for computational chemistry

  2017cited by this paper
• Reinforcement Learning Based Adaptive Sampling: REAPing Rewards by Exploring Protein Conformational Landscapes.

  2017cited by this paper
• Reliable and efficient reaction path and transition state finding for surface reactions with the growing string method

  2017cited by this paper
• Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm.

  2017cited by this paper
• Machine learning unifies the modeling of materials and molecules

  2017cited by this paper
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.

  2017cited by this paper
• The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics

  2017cited by this paper
• Materials discovery and design using machine learning

  2017cited by this paper
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics

  2017cited by this paper
• Nudged elastic band calculations accelerated with Gaussian process regression.

  2017cited by this paper
• Variational encoding of complex dynamics.

  2017cited by this paper
• First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems.

  2017cited by this paper
• Machine learning molecular dynamics for the simulation of infrared spectra

  2017cited by this paper
• Accurate Neural Network Description of Surface Phonons in Reactive Gas–Surface Dynamics: N2 + Ru(0001)

  2017cited by this paper
• Landmark Kernel tICA for Conformational Dynamics

  2017cited by this paper
• Machine Learning and Materials Informatics: Recent Applications and Prospects

  2017cited by this paper
• A universal strategy for the creation of machine learning-based atomistic force fields

  2017cited by this paper
• High-throughput screening of bimetallic catalysts enabled by machine learning

  2017cited by this paper
• Feature engineering of machine-learning chemisorption models for catalyst design

  2017cited by this paper
• Modeling Segregation on AuPd(111) Surfaces with Density Functional Theory and Monte Carlo Simulations

  2017cited by this paper
• Neural network and ReaxFF comparison for Au properties

  2016cited by this paper
• History and Utility of Zeolite Framework-Type Discovery from a Data-Science Perspective

  2016cited by this paper
• Theory-Guided Machine Learning in Materials Science

  2016cited by this paper
• Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks.

  2016cited by this paper
• Quantum-chemical insights from deep tensor neural networks

  2016cited by this paper
• Machine learning of accurate energy-conserving molecular force fields

  2016cited by this paper
• Amp: A modular approach to machine learning in atomistic simulations

  2016cited by this paper
• An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2

  2016cited by this paper
• TPOT: A Tree-based Pipeline Optimization Tool for Automating Machine Learning

  2016cited by this paper
• Automated Discovery and Construction of Surface Phase Diagrams Using Machine Learning.

  2016cited by this paper
• Synergies Between Quantum Mechanics and Machine Learning in Reaction Prediction

  2016cited by this paper
• Synthesis of 'unfeasible' zeolites.

  2016cited by this paper
• Perspective: Machine learning potentials for atomistic simulations.

  2016cited by this paper
• Bypassing the Kohn-Sham equations with machine learning

  2016cited by this paper
• Acceleration of saddle-point searches with machine learning.

  2016cited by this paper
• A study of adatom ripening on an Al (1 1 1) surface with machine learning force fields

  2016cited by this paper
• Machine Learning Force Fields: Construction, Validation, and Outlook

  2016cited by this paper
• Neural network molecular dynamics simulations of solid-liquid interfaces: water at low-index copper surfaces.

  2016cited by this paper
• Machine learning based interatomic potential for amorphous carbon

  2016cited by this paper
• Navigating molecular space for reaction mechanisms: an efficient, automated procedure

  2015cited by this paper
• Grand canonical molecular dynamics simulations of Cu–Au nanoalloys in thermal equilibrium using reactive ANN potentials

  2015cited by this paper
• Deep Learning

  2015cited by this paper
• Machine-Learning-Augmented Chemisorption Model for CO2 Electroreduction Catalyst Screening.

  2015cited by this paper
• Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces.

  2015cited by this paper
• PyEMMA 2: A Software Package for Estimation, Validation, and Analysis of Markov Models.

  2015cited by this paper
• Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

  2015cited by this paper
• Machine learning for quantum mechanics in a nutshell

  2015cited by this paper
• Adaptive machine learning framework to accelerate ab initio molecular dynamics

  2015cited by this paper
• Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach.

  2015cited by this paper
• Constructing high‐dimensional neural network potentials: A tutorial review

  2015cited by this paper
• A benchmark database for adsorption bond energies to transition metal surfaces and comparison to selected DFT functionals

  2015cited by this paper
• The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies

  2015cited by this paper
• Modeling Molecular Kinetics with tICA and the Kernel Trick

  2015cited by this paper
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules

  2015cited by this paper
• Catalysis for production of renewable energy.

  2014cited by this paper
• Insights into the Cr(III) catalyzed isomerization mechanism of glucose to fructose in the presence of water using ab initio molecular dynamics.

  2014cited by this paper
• Benchmarks for Characterization of Minima, Transition States, and Pathways in Atomic, Molecular, and Condensed Matter Systems.

  2014cited by this paper
• Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO2 Capture.

  2014cited by this paper
• Understanding Machine-learned Density Functionals

  2014cited by this paper
• Heterogeneous catalyst discovery using 21st century tools: a tutorial

  2014cited by this paper
• Understanding the composition and activity of electrocatalytic nanoalloys in aqueous solvents: a combination of DFT and accurate neural network potentials.

  2014cited by this paper
• Machine learning of molecular electronic properties in chemical compound space

  2013cited by this paper
• Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.

  2013cited by this paper
• Commentary: The Materials Project: A materials genome approach to accelerating materials innovation

  2013cited by this paper
• Signal Processing

  2013cited by this paper
• Slow dynamics of a protein backbone in molecular dynamics simulation revealed by time-structure based independent component analysis.

  2013cited by this paper
• Kernel Ridge Regression

  2013cited by this paper
• Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)

  2013cited by this paper
• Computational prediction of chemically synthesizable organic structure directing agents for zeolites

  2013cited by this paper

• Perovskite solar cells empowered by machine learning

  2025cites this paper
• Applications of machine learning in surfaces and interfaces

  2025cites this paper
• Optimization and Interpretability Analysis of Machine Learning Methods for ZnO Colloid Particle Size Prediction

  2025cites this paper
• Green Chemistry Approaches for Environmental Pollution Mitigation

  2025cites this paper
• Machine Learning Application in Thermal CO2 Hydrogenation: Catalyst Design, Process Optimization, and Mechanism Insights

  2025cites this paper
• Machine learning-enabled optoelectronic material discovery: a comprehensive review

  2025cites this paper
• Navigating the molecular landscape of environmental science and heavy metal removal: A simulation-based approach

  2024cites this paper
• A mini review on the applications of artificial intelligence (AI) in surface chemistry and catalysis

  2024cites this paper
• Machine learning for CO<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e357" altimg="si33.svg"><mml:msub><mml:mrow /><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msub></mml:math> capture and conversion: A review

  2024cites this paper
• Integrating crystal structure and numerical data for predictive models of lithium-ion battery materials: A modified crystal graph convolutional neural networks approach

  2024cites this paper
• Application of machine learning in perovskite materials and devices: a review

  2024cites this paper
• A review on the role of various machine learning algorithms in microwave-assisted pyrolysis of lignocellulosic biomass waste.

  2024cites this paper
• Machine learning force field study of carboxylate ligands on the surface of zinc-blende CdSe quantum dots

  2024cites this paper
• A mechanistic study of the electrochemical reaction between nitrostyrene and benzaldehyde: DFT calculations on all possible routes and intermediates

  2024cites this paper
• Single atom photocatalytic micropollutants degradation performance: A review

  2024cites this paper
• Hydrogen assisted crack growth rate model derived by physical-guided piecewise symbol regression

  2024cites this paper
• Anti-deactivation of zeolite catalysts for residue fluid catalytic cracking

  2023cites this paper
• An Improved Artificial Neural Network Elastic Constant Prediction Method Based on Particle Swarm Optimization

  2022cites this paper
• Graph-Driven Reaction Discovery: Progress, Challenges, and Future Opportunities

  2022cites this paper
• Machine Learning-Driven Design of Promising Perovskites for Photovoltaic Applications: A Review

  2022cites this paper
• Machine Learning versus Human Learning in Predicting Glass-Forming Ability of Metallic Glasses

  2022cites this paper
• Data-driven probabilistic machine learning in sustainable smart energy/smart energy systems: Key developments, challenges, and future research opportunities in the context of smart grid paradigm

  2022cites this paper
• Determination of the fatigue equation for the cement-stabilized cold recycled mixtures with road construction waste materials based on data-driven

  2022cites this paper
• Machine learning for alloys

  2021cites this paper
• Perspective on computational reaction prediction using machine learning methods in heterogeneous catalysis.

  2021cites this paper
• Computational approaches to dissociative chemisorption on metals: towards chemical accuracy.

  2021cites this paper
• Machine learning for advanced energy materials

  2021cites this paper
• Machine learning for perovskite materials design and discovery

  2021cites this paper
• Training a Model for PredictingAdsorption Energy of Metal Ions Based on Machine Learning

  2021cites this paper
• TMtopo Dataset — Quantum Geometries and Density Topology for 1.1k Transition Metal Complexes

  2021cites this paper
• Linear and nonlinear machine learning correlation of transition metal cluster characteristics

  2021cites this paper
• Machine learning and symbolic regression investigation on stability of MXene materials

  2021cites this paper
• Design of Polymer Blend Electrolytes through a Machine Learning Approach

  2020cites this paper
• From catalyst to process: bridging the scales in modeling the OCM reaction

  2020cites this paper
• Machine learning for CO 2 capture and conversion: A review

  year unknowncites this paper