Scholarlink

<p>These days, finding a reliable way to predict carbon dioxide emissions and suggest ways to cut them has become a shared concern. Thus, the present study applied the artificial neural network to predict carbon dioxide emissions in selected 18 developing countries. The study used seven input variables: green technology, renewable energy, nonrenewable energy, export, import, economic growth, and population. The data used in this study were collected from the World Development Indicators and Organization for Economic Co-operation and Development databases, covering a period from 1990 to 2020. The results show that the best validation performance is observed when the mean squared error is 0.0063142 at epoch 28. Furthermore, the regression value for the entire dataset is 99.9%, which is very close to 1, indicating that the selected variables have a significant impact on CO<sub>2</sub> emissions. The study recommends that to reduce CO<sub>2</sub> emissions and promote sustainable growth, developing countries should prioritize addressing population growth, export and import activities, renewable energy, and nonrenewable energy usage, economic growth, and green technological innovation, which contribute as much as 35.5%, 16.9%, 16.1%, 10%, 9.6%, 7.2%, and 4.6%, respectively, to CO<sub>2</sub> emissions.</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

Carbon Dioxide Emissions Prediction of Selected Developing Countries Using Artificial Neural Network

  • 期刊论文

  • 发表日期：

    2025年3月25日

查看全文
  • Olani Bekele Sakilu,
  • Haibo Chen

摘要

These days, finding a reliable way to predict carbon dioxide emissions and suggest ways to cut them has become a shared concern. Thus, the present study applied the artificial neural network to predict carbon dioxide emissions in selected 18 developing countries. The study used seven input variables: green technology, renewable energy, nonrenewable energy, export, import, economic growth, and population. The data used in this study were collected from the World Development Indicators and Organization for Economic Co-operation and Development databases, covering a period from 1990 to 2020. The results show that the best validation performance is observed when the mean squared error is 0.0063142 at epoch 28. Furthermore, the regression value for the entire dataset is 99.9%, which is very close to 1, indicating that the selected variables have a significant impact on CO2 emissions. The study recommends that to reduce CO2 emissions and promote sustainable growth, developing countries should prioritize addressing population growth, export and import activities, renewable energy, and nonrenewable energy usage, economic growth, and green technological innovation, which contribute as much as 35.5%, 16.9%, 16.1%, 10%, 9.6%, 7.2%, and 4.6%, respectively, to CO2 emissions.