Scholarlink

<p>Artificial intelligence (AI) is being strategically applied to the energy sector, leveraging the unique characteristics of nuclear power to effectively combat climate change. As a zero-carbon emission source, nuclear energy is increasingly vital for a sustainable future. Our study, utilizing an applied System Dynamics (SD) methodology, demonstrates the essential role of generative AI in optimizing nuclear energy’s contribution and mitigating the vulnerabilities of carbon-intensive sources like coal and oil. A comparative analysis between two scenarios, Test 1 and Test 2, reveals generative AI’s superior performance in Test 1, which began with a low initial value. In addition, in the comparison of the four tests, only Test1 shows a higher value than the other test cases, while the remaining test cases have similar values, so the comparison between Test1 and Test2 is valid. In the sensitivity analysis, the fact that Test1 has the largest standard deviation value means that the value of change is the largest. This finding underscores AI’s indispensable capacity to facilitate consensus-building among nations, making the strategic utilization of zero-carbon energy sources a more achievable and collaborative goal.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative analysis of generative AI performance in nuclear energy for climate change mitigation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月6日

查看全文
  • Kyung Bae Jang,
  • Tae Ho Woo

摘要

Artificial intelligence (AI) is being strategically applied to the energy sector, leveraging the unique characteristics of nuclear power to effectively combat climate change. As a zero-carbon emission source, nuclear energy is increasingly vital for a sustainable future. Our study, utilizing an applied System Dynamics (SD) methodology, demonstrates the essential role of generative AI in optimizing nuclear energy’s contribution and mitigating the vulnerabilities of carbon-intensive sources like coal and oil. A comparative analysis between two scenarios, Test 1 and Test 2, reveals generative AI’s superior performance in Test 1, which began with a low initial value. In addition, in the comparison of the four tests, only Test1 shows a higher value than the other test cases, while the remaining test cases have similar values, so the comparison between Test1 and Test2 is valid. In the sensitivity analysis, the fact that Test1 has the largest standard deviation value means that the value of change is the largest. This finding underscores AI’s indispensable capacity to facilitate consensus-building among nations, making the strategic utilization of zero-carbon energy sources a more achievable and collaborative goal.