STAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer Composites
Paper · https://arxiv.org/abs/2610.28709
arXiv:2610.28709v1 Announce Type: new Abstract: Evaluating the energy transmission ratio of an X-ray beam through a polymer composite is a challenging task in radiation shielding studies. The reference solution with Monte Carlo transport simulation is highly accurate but computationally expensive: each of our reference simulations is capped at $4\times10^9$ photon histories and a 20,000 s (over 5 hours) time limit, while closed-form analytical methods fail to represent such complex scenarios. We present an artificial neural network model that maps the unordered multi-set of molecular constituents, their mass fractions, and four bulk physical descriptors directly to the transmission ratio $I(t)/I_0$ in 1-3 milliseconds. The model is a Set Transformer, which makes it permutation invariant by construction and accepts mixtures of different sizes up to 11 constituents within a fixed-size padded set. Each constituent is embedded with a chemistry-pretrained transformer language model, ChemBERTa. In our proposed method, training data are produced by an automated PENELOPE/penEasy pipeline using the radiation source at 30, 80, 100, and 120 kV tube voltages over polyethylene-based shielding composite slabs of thicknesses spanning 0.15-2.5 mm. After preprocessing, the dataset contains $n = 4697$ simulated configurations on which a leakage-free, jointly stratified 10-fold cross-validation is performed, attaining mean squared error MSE = $(1.12 \pm 0.56)\times10^{-4}$, normalized-MSE percentage NMSE% = 0.0294% $\pm$ 0.0147%, and $R^2 = 0.9988$. The corresponding per-sample percentage errors give an alpha-trimmed ($\alpha = 0.10$) absolute percentage error (APE) of 1.66% and a median APE of 1.15%. Our model's inference is several orders of magnitude faster than the underlying Monte Carlo simulation (sub-millisecond per query vs. several hours for the reference run) with effective accuracy in predicting $I(t)/I_0$.
First seen by Oriel on .
AI summary
STAR-XPC uses a permutation-invariant Set Transformer to estimate X-ray transmission through polymer composites in milliseconds, approximating computationally expensive Monte Carlo simulations with high reported accuracy.
- The model combines constituent identities and mass fractions with four bulk physical descriptors, supports mixtures of up to 11 constituents, and embeds chemistry using ChemBERTa.
- Training data comprise 4,697 PENELOPE/penEasy simulations across four tube voltages and composite slab thicknesses from 0.15 to 2.5 mm.
- Leakage-free, jointly stratified 10-fold cross-validation achieved MSE of (1.12 ± 0.56) × 10⁻⁴ and R² of 0.9988.
- The median absolute percentage error was 1.15%; inference takes sub-millisecond per query, compared with several hours for a reference simulation.
#x-ray transmission #polymer composites #set transformers #radiation shielding
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| arXiv AI Papers | oai:arXiv.org:2610.28709v1 | https://arxiv.org/abs/2610.28709 Read discussion |