Charge-Optimized Electrostatic Interaction Atom-Centered Neural Network Algorithm
Machine-learning algorithms have been proposed to capture electrostatic interactions by using effective partial charges. These algorithms often rely on a pretrained model for partial charge prediction using density functional theory-calculated partial charges as references, which introduces complexity to the force field model. The accuracy of the trained model also depends on the reliability of charge partition methods, which can be dependent on the specific system and methodology employed. In this study, we propose an atom-centered neural network (ANN) algorithm that eliminates the need for reference charges. Our algorithm requires only a single NN model for each element to obtain both atomic energy and charges. These atomic charges are then employed to compute electrostatic energies using the Ewald summation algorithm. Subsequently, the force field model is trained on total energy and forces, with the inclusion of electrostatic energy. To evaluate the performance of our algorithm, we conducted tests on three benchmark systems, including a Ge slab with an O adatom system, a TiO2 crystalline system, and a Pd-O nanoparticle system. Our results demonstrate reasonably accurate predictions of partial charges and electrostatic interactions. This algorithm provides a self-consistent charge prediction strategy and possibilities for robust and reliable modeling of electrostatic interactions in machine-learning potentials.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:20 |
|---|---|
| Enthalten in: |
Journal of chemical theory and computation - 20(2024), 5 vom: 12. März, Seite 2088-2097 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Song, Zichen [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 12.03.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1021/acs.jctc.3c01254 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM368706273 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM368706273 | ||
| 003 | DE-627 | ||
| 005 | 20240312233916.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240222s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.jctc.3c01254 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1324.xml |
| 035 | |a (DE-627)NLM368706273 | ||
| 035 | |a (NLM)38380601 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Song, Zichen |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Charge-Optimized Electrostatic Interaction Atom-Centered Neural Network Algorithm |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 12.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Machine-learning algorithms have been proposed to capture electrostatic interactions by using effective partial charges. These algorithms often rely on a pretrained model for partial charge prediction using density functional theory-calculated partial charges as references, which introduces complexity to the force field model. The accuracy of the trained model also depends on the reliability of charge partition methods, which can be dependent on the specific system and methodology employed. In this study, we propose an atom-centered neural network (ANN) algorithm that eliminates the need for reference charges. Our algorithm requires only a single NN model for each element to obtain both atomic energy and charges. These atomic charges are then employed to compute electrostatic energies using the Ewald summation algorithm. Subsequently, the force field model is trained on total energy and forces, with the inclusion of electrostatic energy. To evaluate the performance of our algorithm, we conducted tests on three benchmark systems, including a Ge slab with an O adatom system, a TiO2 crystalline system, and a Pd-O nanoparticle system. Our results demonstrate reasonably accurate predictions of partial charges and electrostatic interactions. This algorithm provides a self-consistent charge prediction strategy and possibilities for robust and reliable modeling of electrostatic interactions in machine-learning potentials | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Han, Jian |e verfasserin |4 aut | |
| 700 | 1 | |a Henkelman, Graeme |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Lei |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of chemical theory and computation |d 2005 |g 20(2024), 5 vom: 12. März, Seite 2088-2097 |w (DE-627)NLM169619249 |x 1549-9626 |7 nnns |
| 773 | 1 | 8 | |g volume:20 |g year:2024 |g number:5 |g day:12 |g month:03 |g pages:2088-2097 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.jctc.3c01254 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 20 |j 2024 |e 5 |b 12 |c 03 |h 2088-2097 | ||