Na₃V₂O₅ / Hard-Carbon / Sn — Na-Ion Electrode Systems (DeepMD)

banner

What this is

DeepMD-kit potentials covering Na₃V₂O₅ (NVO) cathode chemistry and related Sn-based Na-ion anode / hard-carbon interface systems (NVO_Sn, C_Sn particle and multilayer variants) — a broader Na-ion electrode-material survey than a single fixed composition.

Transport properties (NVO/Sn particle systems)

System D (cm²/s) T
nvo_particle 9.21×10⁻¹¹ 300K
nvo_particle 1.18×10⁻¹⁰ 360K
nvo_particle 1.26×10⁻¹⁰ 440K
nvo_sn_p1 8.54×10⁻¹¹ 300K
nvo_sn_p1 1.13×10⁻¹⁰ 360K

AIMD reference: D = 1.1×10⁻¹⁰ cm²/s, Eₐ = 0.27 eV. Mechanical: E = 120 GPa, ν = 0.25.

Files & Validation

File RMSE energy (eV/atom) RMSE force (eV/Å) Training steps Size
model/nvo_sn_primary.pb 0.0135 0.114 4,951,300 9.3 MB
model/nvo_sn_variant2.pb 0.0133 0.122 1,000,000 7.2 MB

RMSE values are validation-set (held-out) energy/force error, read directly from each run's DeepMD-kit lcurve.out at its final training step — not re-derived or estimated.

training convergence

2 of 6 potentials spanning particle-size and phase variants (nvo_particle, nvo_sn phase_1/phase_3, Sn bulk/particle configurations), selected by lowest validation force RMSE; numerous intermediate/scale-study copies exist in the source tree and are not included here.

Training pipeline

AIMD (VASP, PBE) → DeepMD-kit train/freeze/compress. Produced by HPCA (github.com/selvachandrasekaranselvaraj/hpca).

Citation

Selva Chandrasekaran Selvaraj, University of Illinois Chicago.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Selvauma/nvo-deepmd