TorchML_NequIP_GuptaTadmorMartiniani_2024_Si__MO_196181738937_001
| Title
A single sentence description.
|
Parallel NequIP Equivariant GNN for Si developed by Gupta et al. (2024) v001 |
|---|---|
| Description
A short description of the Model describing its key features including for example: type of model (pair potential, 3-body potential, EAM, etc.), modeled species (Ac, Ag, ..., Zr), intended purpose, origin, and so on.
|
A general purpose parallel NequIP equivariant graph neural network (GNN) interatomic potential for Si. The model is trained on the GAP Si PRX (Bartók et al., Phys. Rev. X, 8:041048, 2018) dataset consisting of 2475 configurations, inluding bulk diamond, beta-Sn, hexagonal, bcc, fcc, hcp, liquid, and amorphous silicon configurations, as well as diamond surfaces, vacancies, divacancy, and interstitial faults, and additional rare configurations includingsp2 and sp bonded Si. Given the wide variety of configurations this model was trained on, it is suitable for simulating diverse Si structures. The model has a cutoff radius of 4 angstroms, with the following hyperparameters: maximum order of spherical harmonics set to 1, size of intermediate features set to 64, and the number of graph convolutions set to 3. The model was trained until the error did not improve for 50 validation steps, and an adaptive learning rate < 10^-6 was achieved. |
| Species
The supported atomic species.
| Si |
| Disclaimer
A statement of applicability provided by the contributor, informing users of the intended use of this KIM Item.
|
None |
| Contributor |
Amit Gupta |
| Maintainer |
Amit Gupta |
| Developer |
Amit Gupta Ellad B. Tadmor Stefano Martiniani |
| Published on KIM | 2025 |
| How to Cite |
This Model originally published in [1] is archived in OpenKIM [2-5]. [1] Bartók AP, Kermode J, Bernstein N, Csányi G. Machine learning a general-purpose interatomic potential for silicon. Physical Review X. 2018;8(4):041048. doi:10.1103/PhysRevX.8.041048 [2] Gupta A, Tadmor EB, Martiniani S. Parallel NequIP Equivariant GNN for Si developed by Gupta et al. (2024) v001. OpenKIM; 2025. doi:10.25950/2fce3a4e [3] Gupta A, Karls DS. Torch ML model driver v001. OpenKIM; 2025. doi:10.25950/aefd2d8a [4] Tadmor EB, Elliott RS, Sethna JP, Miller RE, Becker CA. The potential of atomistic simulations and the Knowledgebase of Interatomic Models. JOM. 2011;63(7):17. doi:10.1007/s11837-011-0102-6 [5] Elliott RS, Tadmor EB. Knowledgebase of Interatomic Models (KIM) Application Programming Interface (API). OpenKIM; 2011. doi:10.25950/ff8f563a Click here to download the above citation in BibTeX format. |
| Funding | Not available |
| Short KIM ID
The unique KIM identifier code.
| MO_196181738937_001 |
| Extended KIM ID
The long form of the KIM ID including a human readable prefix (100 characters max), two underscores, and the Short KIM ID. Extended KIM IDs can only contain alpha-numeric characters (letters and digits) and underscores and must begin with a letter.
| TorchML_NequIP_GuptaTadmorMartiniani_2024_Si__MO_196181738937_001 |
| DOI |
10.25950/2fce3a4e https://doi.org/10.25950/2fce3a4e https://commons.datacite.org/doi.org/10.25950/2fce3a4e |
| KIM Item Type
Specifies whether this is a Portable Model (software implementation of an interatomic model); Portable Model with parameter file (parameter file to be read in by a Model Driver); Model Driver (software implementation of an interatomic model that reads in parameters).
| Portable Model using Model Driver TorchML__MD_173118614730_001 |
| Driver | TorchML__MD_173118614730_001 |
| KIM API Version | 2.3 |
| Potential Type | nequip |
| Previous Version | TorchML_NequIP_GuptaTadmorMartiniani_2024_Si__MO_196181738937_000 |
BCC Lattice Constant
This bar chart plot shows the mono-atomic body-centered cubic (bcc) lattice constant predicted by the current model (shown in the unique color) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)Cohesive Energy Graph
This graph shows the cohesive energy versus volume-per-atom for the current mode for four mono-atomic cubic phases (body-centered cubic (bcc), face-centered cubic (fcc), simple cubic (sc), and diamond). The curve with the lowest minimum is the ground state of the crystal if stable. (The crystal structure is enforced in these calculations, so the phase may not be stable.) Graphs are generated for each species supported by the model.
(No matching species)Diamond Lattice Constant
This bar chart plot shows the mono-atomic face-centered diamond lattice constant predicted by the current model (shown in the unique color) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)Dislocation Core Energies
This graph shows the dislocation core energy of a cubic crystal at zero temperature and pressure for a specific set of dislocation core cutoff radii. After obtaining the total energy of the system from conjugate gradient minimizations, non-singular, isotropic and anisotropic elasticity are applied to obtain the dislocation core energy for each of these supercells with different dipole distances. Graphs are generated for each species supported by the model.
(No matching species)FCC Elastic Constants
This bar chart plot shows the mono-atomic face-centered cubic (fcc) elastic constants predicted by the current model (shown in blue) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)FCC Lattice Constant
This bar chart plot shows the mono-atomic face-centered cubic (fcc) lattice constant predicted by the current model (shown in red) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)FCC Stacking Fault Energies
This bar chart plot shows the intrinsic and extrinsic stacking fault energies as well as the unstable stacking and unstable twinning energies for face-centered cubic (fcc) predicted by the current model (shown in blue) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)FCC Surface Energies
This bar chart plot shows the mono-atomic face-centered cubic (fcc) relaxed surface energies predicted by the current model (shown in blue) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)SC Lattice Constant
This bar chart plot shows the mono-atomic simple cubic (sc) lattice constant predicted by the current model (shown in the unique color) compared with the predictions for all other models in the OpenKIM Repository that support the species. The vertical bars show the average and standard deviation (one sigma) bounds for all model predictions. Graphs are generated for each species supported by the model.
(No matching species)Cubic Crystal Basic Properties Table
Species: Si| TorchML_NequIP_GuptaTadmorMartiniani_2024_Si__MO_196181738937_001.txz | Tar+XZ | Linux and OS X archive |
| TorchML_NequIP_GuptaTadmorMartiniani_2024_Si__MO_196181738937_001.zip | Zip | Windows archive |
This Model requires a Model Driver. Archives for the Model Driver TorchML__MD_173118614730_001 appear below.
| TorchML__MD_173118614730_001.txz | Tar+XZ | Linux and OS X archive |
| TorchML__MD_173118614730_001.zip | Zip | Windows archive |