All projects
Computer Science & AI

Investigating Nuclear Energy Production Systems and how Machine Learning can be used to Assess Risks, Detect Anomalies and Improve Decision-Making

Shahan O. ACE International Academy
Nuclear Engineering Artificial Intelligence
Research focus
Nuclear Engineering Artificial Intelligence Energy Systems
Motivation
Safety Sustainability Technological Innovation
About the project

This research explores how machine learning (ML) can revolutionize nuclear energy production by enhancing safety, reliability, and decision-making within reactor systems. It examines the structural and operational vulnerabilities of nuclear power plants—particularly the potential for anomalies and risks that can lead to catastrophic failures—and investigates how ML can be applied to mitigate these challenges.

By reviewing existing literature, analyzing accident case studies, and assessing ML’s integration into energy systems, the paper situates artificial intelligence as both a preventive and predictive tool for next-generation nuclear infrastructure.

The study emphasizes that ML models, through data-driven pattern recognition and predictive analytics, can detect subtle operational anomalies long before human operators can identify them. Applications include real-time sensor data monitoring, early detection of reactor faults, and predictive maintenance for critical systems such as turbines and cooling mechanisms.

The research also outlines the use of reinforcement learning and digital twins to simulate reactor performance, allowing operators to test and optimize conditions virtually without compromising safety. Beyond operational efficiency, ML is proposed as a key enabler in nuclear waste management, where it aids in waste classification, site monitoring, and long-term risk prediction—reducing human exposure and environmental threats.

At a broader level, the paper argues that integrating machine learning into nuclear systems offers a pathway toward safer, more sustainable, and cost-effective energy generation. While acknowledging the high construction costs and environmental impacts of uranium mining, it highlights how automation and data intelligence can reduce human error, prevent system malfunctions, and ensure long-term reactor efficiency.

Ultimately, the study positions ML as an indispensable ally in advancing nuclear energy’s global role as a clean, low-carbon power source—balancing innovation with safety in one of the most sensitive technological domains of modern energy systems.

Your project could be next.

Work one-on-one with a PhD mentor to design, run and publish original research in your field.

Apply now
Boundlearn | RISE Project
Boundlearn
RISE Research Apply now
All projects

Project not found

We couldn’t find that project. Browse the full catalogue instead.

Browse all projects
{{ group }}

{{ title }}

{{ student }} {{ school }}
{{ t }}
Research focus
{{ f }}
Motivation
{{ m }}
About the project

{{ para }}

Your project could be next.

Work one-on-one with a PhD mentor to design, run and publish original research in your field.

Apply now
Shaping Minds, Building Futures. © 2026 Boundlearn LLC. All rights reserved.