Interpolation-Driven Machine Learning Approaches for Plume Shine Dose Estimation: A Comparison of XGBoost, Random Forest, and TabNet

TL;DR

This study compares XGBoost, Random Forest, and TabNet for plume shine dose estimation, demonstrating that interpolation-enhanced datasets improve model accuracy and providing insights into feature importance for safety-critical nuclear applications.

Contribution

It introduces an interpolation-assisted ML framework for radiation dose prediction and compares the performance and interpretability of three different ML models.

Findings

XGBoost achieved the highest prediction accuracy.

Interpolation of datasets improved model performance.

Tree-based models focus on geometric features, while TabNet distributes attention broadly.

Abstract

Despite the success of machine learning (ML) in surrogate modeling, its use in radiation dose assessment is limited by safety-critical constraints, scarce training-ready data, and challenges in selecting suitable architectures for physics-dominated systems. Within this context, rapid and accurate plume shine dose estimation serves as a practical test case, as it is critical for nuclear facility safety assessment and radiological emergency response, while conventional photon-transport-based calculations remain computationally expensive. In this work, an interpolation-assisted ML framework was developed using discrete dose datasets generated with the pyDOSEIA suite for 17 gamma-emitting radionuclides across varying downwind distances, release heights, and atmospheric stability categories. The datasets were augmented using shape-preserving interpolation to construct dense, high-resolution training data. Two tree-based ML models (Random Forest and XGBoost) and one deep learning (DL) model (TabNet) were evaluated to examine predictive performance and sensitivity to dataset resolution. All models showed higher prediction accuracy with the interpolated high-resolution dataset than with the discrete data; however, XGBoost consistently achieved the highest accuracy. Interpretability analysis using permutation importance (tree-based models) and attention-based feature attribution (TabNet) revealed that performance differences stem from how the models utilize input features. Tree-based models focus mainly on dominant geometry-dispersion features (release height, stability category, and downwind distance), treating radionuclide identity as a secondary input, whereas TabNet distributes attention more broadly across multiple variables. For practical deployment, a web-based GUI was developed for interactive scenario evaluation and transparent comparison with photon-transport reference calculations.