Integrating Machine Learning and Monte Carlo Simulations in Nuclear Reaction Modeling and Radiation Transport

Accurate prediction of nuclear reaction cross sections and radiation transport quantities remains a central challenge in nuclear physics, nuclear data evaluation, and applied radiation sciences. Traditional theoretical codes such as TALYS and EMPIRE provide essential frameworks for modeling nuclear reactions, while Monte Carlo-based tools are widely used for simulating particle transport, dose deposition, and radiation-matter interactions. However, discrepancies among experimental data, evaluated libraries, and theoretical predictions still limit the reliability of calculations, particularly in energy regions where measurements are scarce or inconsistent. Machine learning methods now offer complementary tools for improving predictive accuracy, identifying systematic deviations, optimizing model parameters, and supporting uncertainty-aware nuclear data evaluations.

This Research Topic aims to provide a dedicated forum for studies that integrate machine learning algorithms, Monte Carlo simulations, and theoretical nuclear reaction models to improve cross-section predictions, radiation transport modeling, and nuclear data reliability. The main goal is to bring together contributions that bridge physics-based modeling and data-driven approaches, with emphasis on model validation, uncertainty quantification, benchmarking, and practical applications. By combining traditional nuclear reaction codes, evaluated nuclear data libraries, and modern computational methods, this collection seeks to highlight how hybrid approaches can reduce discrepancies between theory and experiment, support the optimization of nuclear model parameters, and improve predictive performance in nuclear physics applications.

We welcome original research articles, reviews, methods papers, and perspective articles addressing the integration of machine learning, Monte Carlo simulations, and nuclear reaction modeling. Topics include:

- ML-enhanced cross-section predictions using XGBoost, random forests, artificial neural networks, Gaussian process regression, LOOCV, and related validation strategies
- Hybrid Monte Carlo and data-driven radiation transport
- Uncertainty quantification, sensitivity analysis, benchmarking, and validation in nuclear data evaluations
- ML-driven optimization of TALYS, EMPIRE, and related theoretical frameworks
- Applications in accelerator-based medical radioisotope production, including yield estimation, target optimization, and radionuclidic impurity assessment.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Curriculum, Instruction, and Pedagogy
• Editorial
• FAIR² Data
• Hypothesis and Theory
• Mini Review
• Original Research
• Perspective
• Review
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Curriculum, Instruction, and Pedagogy
• Editorial
• FAIR² Data
• Hypothesis and Theory
• Mini Review
• Original Research
• Perspective
• Review
• Technology and Code

Keywords: Machine learning; Monte Carlo simulation; nuclear reaction modeling; cross-section prediction; radiation transport; TALYS; EMPIRE; medical radioisotope production; uncertainty quantification; nuclear data

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.