High-risk nuclide screening and parameter sensitivity analysis based on numerical simulation and machine learning

Abstract

During nuclear accidents, large quantities of radionuclides will be released into the environment, posing serious health hazards to local residents. The screening of high-risk nuclides is critical for the development of subsequent nuclear emergency response measures. In order to overcome the shortcomings of traditional screening methods, a machine learning method was proposed to screen high-risk nuclides and predict their contamination to groundwater more effectively. The performances of Support Vector Machine (SVM), Random Forest (RF) and Back Propagation Neural Network (BPNN) algorithms were compared, and sensitivity analyses of the initial leakage concentration ratio (C₀/C_p), distribution coefficient (K_d) and decay coefficient ($\mathit{\lambda }$) on the model outputs were performed. Results showed that RF classification model achieved the highest prediction accuracy for screening high-risk nuclides. The contribution of the input parameters ranked as K_d > $\lambda$ > C₀/C_p. BPNN regression model was found to be the best for predicting when high-risk nuclides would pollute groundwater. The output was negatively correlated with C₀/C_p and positively correlated with K_d and $\lambda$, with the parameter influence ranking as K_d > C₀/C_p > $\lambda$. The contribution of K_d mainly came from itself, and the contribution of C₀/C_p and $\lambda$ mainly due to their interaction with other parameters.