NVIDIA's Linear Radiation Transport dataset provides point-cloud surrogate-modeling data for the final-time 2-D linear Radiation Transport Equation. It covers two canonical benchmarks, including a Lattice benchmark with 707 total samples split into 494 training, 106 validation, and 107 test samples. The dataset was last updated on May 19, 2026.
Use Cases
- Training surrogate models for radiation transport based on point-cloud data structure.
- Benchmarking machine learning methods on physics simulation data based on the described Lattice geometry.
- Validating predictive models for scattering and absorption coefficients based on the discrete design grid variation.
Strengths
- Dataset includes a defined train/validation/test split with 494, 106, and 107 samples respectively.
- Covers two canonical benchmarks varying along complementary axes, as described.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count for the full dataset beyond the Lattice benchmark is unknown, which may limit suitability assessment.
Provenance
- Source
- nvidia
- Collection Method
- Likely generated via simulation for the described canonical benchmarks.
- Freshness
- Last updated 2026-05-19 01:33:01; freshness should be verified.