Rapid assessment of cosmic radiation exposure in aviation based on BP neural network method.

This article focuses on the development of a back propagation (BP) neural network model for real-time and rapid assessment of cosmic radiation exposure to the public during aviation. The model uses a multi-dimensional dataset generated from Monte Carlo-based Geant4 simulations of cosmic ray transport and geomagnetic cutoff rigidity calculations, incorporating parameters such as cosmic ray energy spectrum, Kp-index, time, altitude, latitude, and longitude. The neural network predicts secondary particle spectra at flight altitudes, which are converted into effective dose rates and validated against the International Civil Aviation Organization's (ICAO) CARI-7A model, showing good agreement with differences generally below 20%. The model also evaluates radiation dose increases during solar particle events (SPEs), including ground level enhancements (GLEs), and supports a real-time warning system for aviation radiation exposure based on space weather data.