Automated ReaxFF parametrization using machine learning

Daksha, Chaitanya M.; Yeon, Jejoon; Chowdhury, Sanjib C.; Gillespie, John W.

doi:10.1016/j.commatsci.2020.110107

Cited by 23 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning potential is one of the most critical calculations advances in recent years and has been intensively studied and applied in catalysis [112][113][114][115][116][117][118][119][120][121][122][123][124][125][126][127]. The machine learning potential is a method that uses the machine learning algorithm to find the underneath relationship of the atomic configuration and energy [128].…”

Section: Applications Of Machine Learning In Catalysis 321 Machine Learning Potentialsmentioning

confidence: 99%

Molecular Dynamics and Machine Learning in Catalysts

Liu

Zhu

et al. 2021

Catalysts

View full text Add to dashboard Cite

Given the importance of catalysts in the chemical industry, they have been extensively investigated by experimental and numerical methods. With the development of computational algorithms and computer hardware, large-scale simulations have enabled influential studies with more atomic details reflecting microscopic mechanisms. This review provides a comprehensive summary of recent developments in molecular dynamics, including ab initio molecular dynamics and reaction force-field molecular dynamics. Recent research on both approaches to catalyst calculations is reviewed, including growth, dehydrogenation, hydrogenation, oxidation reactions, bias, and recombination of carbon materials that can guide catalyst calculations. Machine learning has attracted increasing interest in recent years, and its combination with the field of catalysts has inspired promising development approaches. Its applications in machine learning potential, catalyst design, performance prediction, structure optimization, and classification have been summarized in detail. This review hopes to shed light and perspective on ML approaches in catalysts.

show abstract

Section: Applications Of Machine Learning In Catalysis 321 Machine Learning Potentialsmentioning

confidence: 99%

Molecular Dynamics and Machine Learning in Catalysts

Liu

Zhu

et al. 2021

Catalysts

View full text Add to dashboard Cite

show abstract

“…Although it could be predicted quite accurately by DFT, some complex processes such as phase transition and surface/interface properties are still beyond the capacity of quantum methods and require the interatomic potential for classical MD. For materials such as Al, Mo, Ti, and U, phonon properties are evaluated using the temperature‐dependent effective potential method 59–62 . Automatic creation of an interatomic interaction model from scratch is performed to predict the crystal structure of carbon, the high‐pressure phase of sodium, and the allotrope of boron 63 (see Figure 7).…”

Section: Applicationsmentioning

confidence: 99%

Machine‐learning‐based interatomic potentials for advanced manufacturing

Wan

et al. 2021

Int Journal of Mech Sys Dyn

View full text Add to dashboard Cite

This paper summarizes the progress of machine-learning-based interatomic potentials and their applications in advanced manufacturing. Interatomic potential is essential for classical molecular dynamics. The advancements made in machine learning (ML) have enabled the development of fast interatomic potential with ab initio accuracy. The accelerated atomic simulation can greatly transform the design principle of manufacturing technology. The most widely used supervised and unsupervised ML methods are summarized and compared. Then, the emerging interatomic models based on ML are discussed: Gaussian approximation potential, spectral neighbor analysis potential, deep potential molecular dynamics, SCHNET, hierarchically interacting particle neural network, and fast learning of atomistic rare events.

show abstract

“…It is likewise applied to enrich the database of STSMs. There are many new methods such as the new search algorithm, 103 machine learning, 104 data mining, 94 and so on. Thus, simulation can predict from the aspects of the microscopic mechanism of new STSMs and shorten the time cycle from development to market.…”

Section: Simulation Experiment and Theoretical Calculationmentioning

confidence: 99%

Study on the sorption mechanism of middle‐low temperature sorption thermal storage materials from the microscale simulation: A review

2021

View full text Add to dashboard Cite

Middle-low temperature sorption thermal storage materials (STSMs), which are widely applied in the waste heat utilization, can overcome the mismatch of thermal energy between supply and consumption. Many researchers have paid more attention to its complicated mechanism, particularly in the chemisorption process. Unlike the scientific experiment, microscale simulation has an immerse advantage of its low costs, high security, and high precision, which exploring the sorption mechanism at a molecular level. In this review, the microscale simulation method and its application in researching the sorption mechanism are summarized. We mainly stuck in three commonly microscale simulation methods: density functional theory, molecular dynamics, and Monte Carlo method. The diffusion, sorption isotherm and sorption heat, sorption dynamics, chemical reaction pathways, and structural stability are comprehensively examined, which illustrating how the interaction between adsorbate and adsorbent influences the properties of kinetics, thermodynamics, chemistry, and structure.Updating the algorithm, developing the multiscale simulation, establishing a database is promising to extend its application range of design the novel STSMs. Furthermore, as a smart bottom-up method for designing materials, combing with experiment, theoretical calculation, and other burgeoning technology will shorten the time cycle from development to market.

show abstract

Automated ReaxFF parametrization using machine learning

Cited by 23 publications

References 23 publications

Molecular Dynamics and Machine Learning in Catalysts

Molecular Dynamics and Machine Learning in Catalysts

Machine‐learning‐based interatomic potentials for advanced manufacturing

Study on the sorption mechanism of middle‐low temperature sorption thermal storage materials from the microscale simulation: A review

Contact Info

Product

Resources

About