Twofold Machine-Learning and Molecular Dynamics: A Computational Framework
Data science and machine learning (ML) techniques are employed to shed light into the molecular mechanisms that affect fluid-transport properties at the nanoscale. Viscosity and thermal conductivity values of four basic monoatomic elements, namely, argon, krypton, nitrogen, and oxygen, are gathered...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/13/1/2 |
| _version_ | 1797344357709250560 |
|---|---|
| author | Christos Stavrogiannis Filippos Sofos Maria Sagri Denis Vavougios Theodoros E. Karakasidis |
| author_facet | Christos Stavrogiannis Filippos Sofos Maria Sagri Denis Vavougios Theodoros E. Karakasidis |
| author_sort | Christos Stavrogiannis |
| collection | DOAJ |
| description | Data science and machine learning (ML) techniques are employed to shed light into the molecular mechanisms that affect fluid-transport properties at the nanoscale. Viscosity and thermal conductivity values of four basic monoatomic elements, namely, argon, krypton, nitrogen, and oxygen, are gathered from experimental and simulation data in the literature and constitute a primary database for further investigation. The data refers to a wide pressure–temperature (P-T) phase space, covering fluid states from gas to liquid and supercritical. The database is enriched with new simulation data extracted from our equilibrium molecular dynamics (MD) simulations. A machine learning (ML) framework with ensemble, classical, kernel-based, and stacked algorithmic techniques is also constructed to function in parallel with the MD model, trained by existing data and predicting the values of new phase space points. In terms of algorithmic performance, it is shown that the stacked and tree-based ML models have given the most accurate results for all elements and can be excellent choices for small to medium-sized datasets. In such a way, a twofold computational scheme is constructed, functioning as a computationally inexpensive route that achieves high accuracy, aiming to replace costly experiments and simulations, when feasible. |
| first_indexed | 2024-03-08T11:01:11Z |
| format | Article |
| id | doaj.art-6c089051d63f4264beeb632aa6808ceb |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-08T11:01:11Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-6c089051d63f4264beeb632aa6808ceb2024-01-26T15:52:14ZengMDPI AGComputers2073-431X2023-12-01131210.3390/computers13010002Twofold Machine-Learning and Molecular Dynamics: A Computational FrameworkChristos Stavrogiannis0Filippos Sofos1Maria Sagri2Denis Vavougios3Theodoros E. Karakasidis4Department of Physics, University of Thessaly, 35100 Lamia, GreeceDepartment of Physics, University of Thessaly, 35100 Lamia, GreeceDepartment of Physics, University of Thessaly, 35100 Lamia, GreeceDepartment of Physics, University of Thessaly, 35100 Lamia, GreeceDepartment of Physics, University of Thessaly, 35100 Lamia, GreeceData science and machine learning (ML) techniques are employed to shed light into the molecular mechanisms that affect fluid-transport properties at the nanoscale. Viscosity and thermal conductivity values of four basic monoatomic elements, namely, argon, krypton, nitrogen, and oxygen, are gathered from experimental and simulation data in the literature and constitute a primary database for further investigation. The data refers to a wide pressure–temperature (P-T) phase space, covering fluid states from gas to liquid and supercritical. The database is enriched with new simulation data extracted from our equilibrium molecular dynamics (MD) simulations. A machine learning (ML) framework with ensemble, classical, kernel-based, and stacked algorithmic techniques is also constructed to function in parallel with the MD model, trained by existing data and predicting the values of new phase space points. In terms of algorithmic performance, it is shown that the stacked and tree-based ML models have given the most accurate results for all elements and can be excellent choices for small to medium-sized datasets. In such a way, a twofold computational scheme is constructed, functioning as a computationally inexpensive route that achieves high accuracy, aiming to replace costly experiments and simulations, when feasible.https://www.mdpi.com/2073-431X/13/1/2machine learningmolecular dynamicsthermal conductivityshear viscosity |
| spellingShingle | Christos Stavrogiannis Filippos Sofos Maria Sagri Denis Vavougios Theodoros E. Karakasidis Twofold Machine-Learning and Molecular Dynamics: A Computational Framework Computers machine learning molecular dynamics thermal conductivity shear viscosity |
| title | Twofold Machine-Learning and Molecular Dynamics: A Computational Framework |
| title_full | Twofold Machine-Learning and Molecular Dynamics: A Computational Framework |
| title_fullStr | Twofold Machine-Learning and Molecular Dynamics: A Computational Framework |
| title_full_unstemmed | Twofold Machine-Learning and Molecular Dynamics: A Computational Framework |
| title_short | Twofold Machine-Learning and Molecular Dynamics: A Computational Framework |
| title_sort | twofold machine learning and molecular dynamics a computational framework |
| topic | machine learning molecular dynamics thermal conductivity shear viscosity |
| url | https://www.mdpi.com/2073-431X/13/1/2 |
| work_keys_str_mv | AT christosstavrogiannis twofoldmachinelearningandmoleculardynamicsacomputationalframework AT filippossofos twofoldmachinelearningandmoleculardynamicsacomputationalframework AT mariasagri twofoldmachinelearningandmoleculardynamicsacomputationalframework AT denisvavougios twofoldmachinelearningandmoleculardynamicsacomputationalframework AT theodorosekarakasidis twofoldmachinelearningandmoleculardynamicsacomputationalframework |