Xin Zhang, Yanjun Zhang, Yu Zhang, Yuxiang Cheng, Qiangbin Liu, Hao Deng, Yongjie Ma, Lin Bai, Lei Liu
{"title":"High-risk nuclide screening and parameter sensitivity analysis based on numerical simulation and machine learning","authors":"Xin Zhang, Yanjun Zhang, Yu Zhang, Yuxiang Cheng, Qiangbin Liu, Hao Deng, Yongjie Ma, Lin Bai, Lei Liu","doi":"10.1016/j.jhazmat.2024.136002","DOIUrl":null,"url":null,"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 (<em>C</em><sub><em>0</em></sub><em>/C</em><sub><em>p</em></sub>), distribution coefficient (<em>K</em><sub><em>d</em></sub>) and decay coefficient (<span><math><mi is=\"true\" mathvariant=\"bold-italic\">λ</mi></math></span>) 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 <em>K</em><sub><em>d</em></sub> > <span><math><mi is=\"true\">λ</mi></math></span> > <em>C</em><sub><em>0</em></sub><em>/C</em><sub><em>p</em></sub>. BPNN regression model was found to be the best for predicting when high-risk nuclides would pollute groundwater. The output was negatively correlated with <em>C</em><sub><em>0</em></sub><em>/C</em><sub><em>p</em></sub> and positively correlated with <em>K</em><sub><em>d</em></sub> and <span><math><mi is=\"true\">λ</mi></math></span>, with the parameter influence ranking as <em>K</em><sub><em>d</em></sub> > <em>C</em><sub><em>0</em></sub><em>/C</em><sub><em>p</em></sub> > <span><math><mi is=\"true\">λ</mi></math></span>. The contribution of <em>K</em><sub><em>d</em></sub> mainly came from itself, and the contribution of <em>C</em><sub><em>0</em></sub><em>/C</em><sub><em>p</em></sub> and <span><math><mi is=\"true\">λ</mi></math></span> mainly due to their interaction with other parameters.","PeriodicalId":361,"journal":{"name":"Journal of Hazardous Materials","volume":null,"pages":null},"PeriodicalIF":12.2000,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hazardous Materials","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1016/j.jhazmat.2024.136002","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
引用次数: 0
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/Cp), distribution coefficient (Kd) and decay coefficient () 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 Kd > > C0/Cp. 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/Cp and positively correlated with Kd and , with the parameter influence ranking as Kd > C0/Cp > . The contribution of Kd mainly came from itself, and the contribution of C0/Cp and mainly due to their interaction with other parameters.
期刊介绍:
The Journal of Hazardous Materials serves as a global platform for promoting cutting-edge research in the field of Environmental Science and Engineering. Our publication features a wide range of articles, including full-length research papers, review articles, and perspectives, with the aim of enhancing our understanding of the dangers and risks associated with various materials concerning public health and the environment. It is important to note that the term "environmental contaminants" refers specifically to substances that pose hazardous effects through contamination, while excluding those that do not have such impacts on the environment or human health. Moreover, we emphasize the distinction between wastes and hazardous materials in order to provide further clarity on the scope of the journal. We have a keen interest in exploring specific compounds and microbial agents that have adverse effects on the environment.