辐射研究与辐射工艺学报2025，Vol.43Issue(6)：102-113,12.DOI:10.11889/j.1000-3436.2025-0057
基于TCN-BiLSTM混合神经网络模型的核素扩散浓度预测方法
Prediction of radionuclide dispersion concentration based on TCN-BiLSTM model
摘要
Abstract
To meet the demand for rapid prediction of radionuclide dispersion in nuclear emergency response,this study proposes a hybrid TCN-BiLSTM model for fast concentration forecasting.Temporal features are extracted by the TCN,while bidirectional dependencies are captured by the BiLSTM.Training data are generated using realistic terrain and meteorological inputs with a Lagrangian dispersion model.The model is validated on the Kincaid SF6 tracer experiment dataset in Illinois,USA,and further applied to a simulated 137Cs release case.Results show that prediction errors remain below 2%,and compared with a standalone TCN,the hybrid model reduces MAE and RMSE by 29.7%and 33.3%,respectively,demonstrating its efficiency and accuracy for rapid radionuclide dispersion prediction.关键词
时序卷积网络/双向长短期记忆网络/核素大气扩散/浓度预测Key words
Temporal convolutional network/Bidirectional long short-term memory/Radionuclide atmospheric dispersion/Concentration prediction分类
能源科技引用本文复制引用
王箫箫,杨子辉,艾雨星,李煜辰,莫紫雯,袁振豪,李桃生..基于TCN-BiLSTM混合神经网络模型的核素扩散浓度预测方法[J].辐射研究与辐射工艺学报,2025,43(6):102-113,12.基金项目
安徽省自然科学基金(2008085MA23)、合肥物质科学研究院院长基金(YZJJ202208-TS)、科工局乏燃料后处理专项 Supported by Natural Science Foundation of Anhui Province(2008085MA23),Director's Fund of Hefei Institutes of Physical Science,CAS(YZJJ202208-TS),and The Spent Fuel Reprocessing Research Project （2008085MA23）
