방사선량률 예측을 위한 기계학습 기반 모델 개발 및 최적화 연구

Abstract

In recent years, radiation has become a socially important issue, increasing the need foraccurate prediction of radiation levels. In this study, machine learning-based models such as MultipleLinear Regression (MLR), Random Forest (RF), XGBoost, and LightGBM, which predict the dose rate bytime (nSv h-1) by selecting only important variables, were used, and the correlation between temperature,humidity, cumulative precipitation, wind direction, wind speed, local air pressure, sea pressure, solarradiation, and radiation dose rate (nSv h-1) was analyzed by collecting weather data and radiation doserate for about 6 months in Jangseong, Jeollanam-do. As a result of the evaluation based on the RMSE(Root Mean Squared Error) and R-Squared (R-Squared coefficient of determination) scores, the RMSEof the XGBoost model was 22.92 and the R-Squared was 0.73, showing the best performance amongthe models used. As a result of optimizing hyperparameters of all models using the GridSearch methodand comparing them by adding variables inside the measuring instrument, it was confirmed that theperformance improved to 2.39 for RMSE and 0.99 for R-Squared in both XGBoost and LightGBM.