Advanced Data Analytics and Machine Learning for Geospatial Interpolation, Anomaly Detection, Background Prediction...

Area of Science:

• Environmental Science
• Nuclear Engineering
• Data Science

Background:

• Spatial analysis of radiation levels is critical for identifying hazards and mitigating health risks.
• Traditional radiation monitoring lacks advanced analytics for emergency response.
• Machine learning offers potential for predictive radiation monitoring and anomaly detection.

Purpose of the Study:

• To develop advanced analytics for radiation monitoring, including interpolation, anomaly detection, and machine learning-based prediction.
• To plan emergency evacuation routes with minimal radiation exposure using the A* algorithm.
• To enhance decision-making for radiation protection professionals and public officials.

Main Methods:

• Utilized an IoT-connected mobile radiation detector for real-time data collection.
• Applied various interpolation techniques for radiation mapping.
• Implemented machine learning models for background radiation prediction and anomaly detection.
• Employed the A* algorithm for emergency escape route planning, adhering to the ALARA principle.

Main Results:

• Generated interpolated radiation heatmaps for visualization.
• Successfully detected anomalies in radiation levels.
• Evaluated machine learning models for accurate background radiation prediction.
• Determined optimized emergency escape routes prioritizing minimal radiation exposure.

Conclusions:

• The integration of advanced analytics and machine learning revolutionizes radiation monitoring systems.
• This approach significantly improves situational awareness and emergency response capabilities.
• The study provides a framework for developing effective radiation protection strategies and safeguarding public health.