Advancing Nuclear Engineering through Artificial Intelligence and Machine Learning

Recent advancements in Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) have significantly increased interest among nuclear scientists in these technologies. However, several challenges hinder their widespread adoption in the nuclear community. For instance, nuclear engineering data often exhibits unique characteristics based on the type of analysis, reactor, and physical phenomena. This necessitates tailored adjustments to AI/ML/DL algorithms. Additionally, these methods require thorough validation and comparison, yet there are limited benchmarks and case studies available. Moreover, gaps exist in quantifying the predictive capabilities of AI/ML/DL models.

To enable more reliable and credible applications of AI/ML/DL in high-consequence systems like nuclear reactors, which are subject to stringent safety regulations, these critical issues must be addressed.

The performance of AI, ML, and DL in the modeling and simulation of reactor systems must be thoroughly evaluated to provide essential guidelines to the nuclear community about research and development needs for reliable AI/ML/DL applications in nuclear modeling and simulation.

The predictive capabilities and credibility of AI/ML/DL must be established and improved through consistent, extensive, and technically sound verification, validation, and uncertainty quantification. Innovative approaches must be developed to address challenges such as data scarcity, scaling-related uncertainty, and the lack of physics in black-box AI/ML/DL models.

Enhancing the trustworthiness of AI/ML/DL in nuclear applications is necessary for broad acceptance by regulators, stakeholders, and decision-makers. Emphasizing accuracy, robustness, reproducibility, transparency, and explainability is of particular importance.

This Research Topic explores emerging research trends and challenges in developing and applying AI, ML, and DL methods to nuclear engineering problems.

Areas within the scope of this collection include:
• Benefits of AI/ML/DL for current and future nuclear power plants
• Challenges and shortcomings of deploying AI/ML/DL in nuclear power plants
• Performance assessment of AI/ML/DL in the modeling and simulation of nuclear systems
• Verification, validation, and uncertainty quantification for AI/ML/DL methods in nuclear modeling and simulation
• Trustworthiness, robustness, and explainability of AI/ML/DL technologies
• Digital twins for complex nuclear systems
• AI/ML/DL to support nuclear safety, risk analyses, and risk-informed decision making
• AI/ML/DL for prognostics and health management of nuclear systems
• Design and regulation of nuclear systems with AI/ML/DL
• Human-machine interaction issues and potential resolutions
• AI tools for nuclear safety cases and compliance
• Lessons learned from case studies and proven practices.

Article types and fees

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

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• ... 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
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review
• Technology and Code

Keywords: artificial intelligence, machine learning, deep learning, nuclear engineering, VVUQ, explainability, interpretability, human-machine interactions, nuclear systems, digital twins, prognostics, health management, nuclear power plants, safety, Neutronics, instrumentation, control, nuclear reactors

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.