Comparing Surrogate Models for the Dissolution of Spent Nuclear Fuel

Faculty Mentor

Dr. Michele Joyner

Mentor Home Department

Mathematics

Short Abstract

The goal of this study is to analyze the performance of surrogate models for the spread of nuclear contamination. Machine learning techniques are of particular interest since they typically can generate models to a high degree of accuracy while also using far fewer computational resources. Specifically, we seek to explore the use of Neural Networks and use them to create a more accurate model than the surrogate model provided through a study conducted through Sandia National Labs.

Category

Science and Technology

Start Date

24-4-2023 1:30 PM

End Date

24-4-2023 1:45 PM

Location

D.P. Culp Center Room 219

This document is currently not available here.

Share

COinS
 
Apr 24th, 1:30 PM Apr 24th, 1:45 PM

Comparing Surrogate Models for the Dissolution of Spent Nuclear Fuel

D.P. Culp Center Room 219

The goal of this study is to analyze the performance of surrogate models for the spread of nuclear contamination. Machine learning techniques are of particular interest since they typically can generate models to a high degree of accuracy while also using far fewer computational resources. Specifically, we seek to explore the use of Neural Networks and use them to create a more accurate model than the surrogate model provided through a study conducted through Sandia National Labs.