INTELLIGENT MONITORING FOR DETECTIONS AND ESTIMATING RADIOLOGICAL PLUME DISPERSION IN AQUATIC ENVIRONMENTS: RIVERS AND SEAS

This work continues the presentation INTELLIGENT MONITORING FOR RADIOLOGICAL PLUME DISPERSION ESTIMATION - INTELLIGENT MONITORING FOR RADIOLOGICAL PLUM DISPERSION ESTIMATION, developed as part of the event hosted by ABDAN at the third edition of the Nuclear Trade & Technology Exchange – NT2E, Brazilian Nuclear Olympics (ONB), Hackapower. The primary objective was to develop a system for monitoring radiological plumes in aquatic environments, using a model based on Gaussian Process Regression (GPR) and Particle Swarm Optimization (PSO). The proposed system aims to estimate radiation dispersion in scenarios where plant systems are unavailable, similar to the Fukushima accident. Given this context, it was necessary to create mobile devices with radiation detection capabilities to provide accurate data on dose rate distribution. The model was developed to predict dose distribution using simulated data from a hypothetical accident and involved the use of LoRaWAN networks for drone communication and a firefly algorithm for signaling areas with different radiation levels. The implementation of GPR utilized the ScikitLearn library, while PSO was applied through the pyswarm library, focusing on optimization based on information entropy. Results indicated that the model successfully reconstructed the dose rate profile with an estimate close to the actual values, although data non-uniformity may have impacted accuracy. The use of drones for data collection proved innovative and effective, enabling real-time analysis and offering a robust solution for radiological monitoring in emergency scenarios. Analysis of radiation permeability variation in different aquatic environments highlighted the importance of adjusting measurements according to water density and composition. In conclusion, the work achieved its goal by developing an intelligent system for radiation dispersion estimation, and future work should explore new scenarios and dynamics to enhance model accuracy in real radiological emergency situations.