High-fidelity synthetic simulations of nanoscale ion transport generated from stochastic Poisson–Nernst–Planck equations under thermally fluctuating and dissipative conditions. The dataset was developed by Naman Dixit and is distributed as cross-platform NumPy datasets and a unified HDF5 archive for large-scale scientific machine learning workflows. It contains spatial ion concentration fields, electrostatic potential distributions, transport trajectories, and derived physical observables across multiple transport regimes.
Use Cases
- Supervised operator learning based on discretized one-dimensional transport fields and their corresponding future states
- Dynamical forecasting and long-horizon predictive analysis based on simulated transport trajectories
- Inverse modeling and dynamical reconstruction based on transport fields and stochastic forcing terms
- Benchmarking data-driven operator-learning frameworks under stochastic electrodiffusion and dissipative transport conditions
Strengths
- Includes a unified production-scale compressed HDF5 archive (`operator_dataset.h5`) consolidating transport fields, simulation outputs, physical parameters, and derived statistical metrics
- Designed for reproducible research with cross-platform training, validation, and testing NumPy datasets
- Contains multiple simulated scenarios including low-noise diffusion, stochastic electrodiffusion, and strongly perturbed nonequilibrium conditions
Limitations
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
- Last updated 2026-06-25 13:31:31; freshness should be verified
Provenance
- Source
- Naman Dixit Dataverse
- Collection Method
- Synthetic simulations generated from stochastic Poisson–Nernst–Planck equations
- Freshness
- Last updated 2026-06-25 13:31:31