Hybrid modeling approach to improve the forecasting capability for the gaseous radionuclide in a nuclear site

作者：Jeong Hyojoon^*; Hwang Wontae; Kim Eunhan; Han Moonhee

来源：Annals of Nuclear Energy, 2012, 42: 30-34.

DOI：10.1016/j.anucene.2011.11.012

• Hybrid modeling
• ISC
• ANFIS
• Environmental impact assessment

Predicted air concentrations of radioactive materials are important for an environmental impact assessment for the public health. In this study, the performance of a hybrid modeling combined with the industrial source complex (ISC) model and an adaptive neuro-fuzzy inference system (ANFIS) for predicting tracer concentrations was investigated. Tracer dispersion experiments were performed to produce the field data assuming the accidental release of radioactive material. ANFIS was trained in order that the outputs of the ISC model are similar to the measured data. Judging from the higher correlation coefficients between the measured and the calculated ones, the hybrid modeling approach could be an appropriate technique for an improvement of the modeling capability to predict the air concentrations for radioactive materials.

• 出版日期2012-4