Feasibility of neural network metamodels for emulation and sensitivity analysis of radionuclide transport models

Author:

Turunen Jari,Lipping Tarmo

Abstract

AbstractIn this paper we compare the outputs of neural network metamodels with numerical solutions of differential equation models in modeling cesium-137 transportation in sand. Convolutional neural networks (CNNs) were trained with differential equation simulation results. Training sets of various sizes (from 5120 to 163,840) were used. First order and total order Sobol methods were applied to both models in order to test the feasibility of neural network metamodels for sensitivity analysis of a radionuclide transport model. Convolutional neural networks were found to be capable of emulating the differential equation models with high accuracy when the training set size was 40,960 or higher. Neural network metamodels also gave similar results compared with the numerical solutions of the partial differential equation model in sensitivity analysis.

Funder

Horizon 2020 EURAD

Publisher

Springer Science and Business Media LLC

Subject

Multidisciplinary

Reference29 articles.

1. Gephart, R. E. & Lundgren, R. E. Hanford tank clean up: A guide to understanding the technical issues. Tech. Rep., Pacific Northwest Laboratory, Richland, Washington (1995).

2. Wikipedia. Hanford Site. https://en.wikipedia.org/wiki/Hanford_Site (2022). Accessed: 2022-08-23.

3. National Research Council. Improving the Scientific Basis for Managing DOE’s Excess Nuclear Materials and Spent Nuclear Fuel (The National Academies Press, Washington, DC, 2003).

4. Hanford.gov. Annual Reports. https://www.hanford.gov/page.cfm/SoilGroundwaterAnnualReports (2022). Accessed: 2022-08-24.

5. Toader, M. & Vasilache, R. A. Cancer Risk Due to Cs-137 and Sr-90 Dietary Intake After the Chernobyl Accident. In International conference on one decade after Chernobyl: summing up the radiological consequences of the accident, 104–110 (IAEA, Vienna, 1997).

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3