Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-objective Combinatorial Methodology for Nuclear Reactor Site Assessment: A Case Study for the United States

Omer Erdem, Kevin Daley, Gabrielle Hoelzle, Majdi I. Radaideh

TL;DR

The paper tackles high capital costs and siting bias in nuclear plant location by proposing a bias-free, multi-objective combinatorial framework that evaluates over $30{,}000$ sites using $22$ objectives. It combines exhaustive Pareto-front analysis with two data-driven models, ConcNN and LUT-NN, to predict siting metrics and objective importance, enabling rapid nationwide assessments from location coordinates. Key findings show coal power plant sites are highly competitive for nuclear development, with some Brownfield sites also viable, and four CPPs plus two Brownfields ranking among the top locations. The approach enhances transparency and scalability for siting decisions, offering a pathway to cost-effective, sustainable nuclear infrastructure and potential applicability to other countries; data and models are publicly accessible for further research.

Abstract

As clean energy demand grows to meet sustainability and net-zero goals, nuclear energy emerges as a reliable option. However, high capital costs remain a challenge for nuclear power plants (NPP), where repurposing coal power plant sites (CPP) with existing infrastructure is one way to reduce these costs. Additionally, Brownfield sites-previously developed or underutilized lands often impacted by industrial activity-present another compelling alternative. This study introduces a novel multi-objective optimization methodology, leveraging combinatorial search to evaluate over 30,000 potential NPP sites in the United States. Our approach addresses gaps in the current practice of assigning pre-determined weights to each site attribute that could lead to bias in the ranking. Each site is assigned a performance-based score, derived from a detailed combinatorial analysis of its site attributes. The methodology generates a comprehensive database comprising site locations (inputs), attributes (outputs), site score (outputs), and the contribution of each attribute to the site score. We then use this database to train a neural network model, enabling rapid predictions of nuclear siting suitability across any location in the United States. Our findings highlight that CPP sites are highly competitive for nuclear development, but some Brownfield sites are able to compete with them. Notably, four CPP sites in Ohio, North Carolina, and New Hampshire, and two Brownfield sites in Florida and California rank among the most promising locations. These results underscore the potential of integrating machine learning and optimization techniques to transform nuclear siting, paving the way for a cost-effective and sustainable energy future.

Multi-objective Combinatorial Methodology for Nuclear Reactor Site Assessment: A Case Study for the United States

TL;DR

The paper tackles high capital costs and siting bias in nuclear plant location by proposing a bias-free, multi-objective combinatorial framework that evaluates over sites using objectives. It combines exhaustive Pareto-front analysis with two data-driven models, ConcNN and LUT-NN, to predict siting metrics and objective importance, enabling rapid nationwide assessments from location coordinates. Key findings show coal power plant sites are highly competitive for nuclear development, with some Brownfield sites also viable, and four CPPs plus two Brownfields ranking among the top locations. The approach enhances transparency and scalability for siting decisions, offering a pathway to cost-effective, sustainable nuclear infrastructure and potential applicability to other countries; data and models are publicly accessible for further research.

Abstract

As clean energy demand grows to meet sustainability and net-zero goals, nuclear energy emerges as a reliable option. However, high capital costs remain a challenge for nuclear power plants (NPP), where repurposing coal power plant sites (CPP) with existing infrastructure is one way to reduce these costs. Additionally, Brownfield sites-previously developed or underutilized lands often impacted by industrial activity-present another compelling alternative. This study introduces a novel multi-objective optimization methodology, leveraging combinatorial search to evaluate over 30,000 potential NPP sites in the United States. Our approach addresses gaps in the current practice of assigning pre-determined weights to each site attribute that could lead to bias in the ranking. Each site is assigned a performance-based score, derived from a detailed combinatorial analysis of its site attributes. The methodology generates a comprehensive database comprising site locations (inputs), attributes (outputs), site score (outputs), and the contribution of each attribute to the site score. We then use this database to train a neural network model, enabling rapid predictions of nuclear siting suitability across any location in the United States. Our findings highlight that CPP sites are highly competitive for nuclear development, but some Brownfield sites are able to compete with them. Notably, four CPP sites in Ohio, North Carolina, and New Hampshire, and two Brownfield sites in Florida and California rank among the most promising locations. These results underscore the potential of integrating machine learning and optimization techniques to transform nuclear siting, paving the way for a cost-effective and sustainable energy future.

Paper Structure

This paper contains 18 sections, 22 equations, 12 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Data Collection and Processing
  3. Rationale for Objective Selection
  4. Socioeconomic Characteristics
  5. Safety Characteristics
  6. Proximity Characteristics
  7. Coal Power Plant Sites
  8. Research Methodology
  9. Non-Dominated, Multi-Objective Combinatorial Search
  10. Concatenated Neural Networks (ConcNN)
  11. Lookup Table Plus Neural Networks (LUT-NN)
  12. Computing Resources
  13. Results and Discussions
  14. Reactor Siting Analysis in the United States
  15. ConcNN Model Results
  16. ...and 3 more sections

Figures (12)

  • Figure 1: acres Brownfield locations in the United States provided by the Environmental Protection Agency.
  • Figure 2: A flowchart of the multi-objective combinatorial analysis for nuclear reactor sites proposed in this study.
  • Figure 3: Visualization of the data flow of the ConcNN model (Concatenated Neural Network).
  • Figure 4: Visualization of the data flow of the LUT-NN model (Lookup Table Plus Neural Networks).
  • Figure 5: A flowchart summarizing how the site data are combined and processed to feed into the machine learning models
  • ...and 7 more figures