Sign in Subscribe
Global warming

Accurate Carbon Emission Forecasting Crucial for Sustainable Development

Strategic Insights

— 2 min read

Researchers at the Xi'an University of Architecture and Technology have published a study highlighting the importance of accurately identifying key factors influencing carbon emissions and forecasting future emission trajectories for policymaking and achieving sustainable development. The study focused on the city-industry scale, a often overlooked level of analysis in existing research. By developing a carbon emission prediction framework, the researchers aimed to provide a more accurate understanding of the factors driving emissions in the nonferrous metals industry in Shaanxi Province, China.

Key Takeaways:

  • The study identified six factors significantly influencing carbon emissions in the nonferrous metals industry, including socio-economic and sectoral energy consumption data.
  • A backpropagation neural network optimized by the particle swarm optimization algorithm (PSO-BPNN) was constructed to conduct scenario-based carbon emission forecasts for the period 2022-2035.
  • The results showed that the PSO-BPNN model exceeds the traditional BPNN model in terms of prediction accuracy, achieving a coefficient of determination (R-2) of 0.996.
  • The study found that under the baseline and high-carbon scenarios, carbon emissions will continue to rise, while under the low-carbon scenario, emissions are projected to peak in 2028 at 6.34 million tons.
  • The research concluded that the findings offer theoretical support for emission reduction policymaking in regions with huge energy consumption and carbon emissions.
  • The study provides a novel application of the PSO-BPNN model in predicting carbon emissions, which can be used as a decision-making tool for policymakers and stakeholders.

Statistics:

  • The PSO-BPNN model achieved a coefficient of determination (R-2) of 0.996, a mean absolute percentage error (MAPE) of 0.010%, a root mean square error (RMSE) of 2.397%, and a mean absolute error (MAE) of 2.022%.
  • Under the baseline scenario, carbon emissions are projected to rise from 6.17 million tons in 2022 to 7.43 million tons in 2035.
  • Under the high-carbon scenario, emissions are projected to rise from 6.17 million tons in 2022 to 10.51 million tons in 2035.
  • Under the low-carbon scenario, emissions are projected to peak in 2028 at 6.34 million tons.

Sources:

  • Environment, Development and Sustainability, 2025. "The Analysis of Carbon Emissions In Urban Nonferrous Metals Industry With Neural Network Model."
  • Xi'an University of Architecture and Technology. "Findings from Xi'an University of Architecture and Technology in the Area of Global Warming and Climate Change Described (The Analysis of Carbon Emissions In Urban Nonferrous Metals Industry With Neural Network Model)." Global Warming Focus. October 13, 2025; p 129.

Read more