2023 Vol.6 Oct.N05

• Title: Method for predicting urban carbon emissions under the background of big data
• Name: Yaoning YANG
• Company: 1.Key Laboratory of New Technology for Construction of Cities in Mountain Area, Ministry of Education, Chongqing University, Chongqing, 400045 China 2.Institute for Urban Design and Sustainable Urban Planning, Technical University of Berlin, Berlin, 10623
• Abstract:

  With the acceleration of urbanization and economic development, urban carbon emissions have become one of the main contributors to global climate change issues. Therefore, accurately predicting urban carbon emissions has important application value. This article proposes a machine learning based prediction method for predicting urban carbon emissions in the context of big data. Firstly, by analyzing and screening the influencing factors of urban carbon emissions, multiple factors such as economy, energy, transportation, and population were selected as prediction indicators. Then, a variety of machine learning algorithms are used to predict, including support vector machine, random forest, deep learning and other methods. Finally, by comparing the advantages and disadvantages of each algorithm, we determined to select the optimal random forest algorithm to predict urban carbon emissions, and proposed carbon emission reduction policy recommendations based on big data.

  
  

• Keyword: Big data; Urban carbon emissions; Carbon emission prediction
• DOI: 10.12250/jpciams2023090707
• Citation form: Yaoning YANG .Method for predicting urban carbon emissions under the background of big data [J]. Computer Informatization and Mechanical System,2023,Vol.6,pp.29-32

References

[1] SASAKI, NOPHEA, MYINT, YADANAR YE, ABE, ISSEI, et al. Predicting carbon emissions, emissions reductions, and carbon removal due to deforestation and plantation forests in Southeast Asia[J]. 2021,312(20):1-12.

[2] XIE ZEQIONG, GAO XUENONG, YUAN WENHUI, et al. Decomposition and prediction of direct residential carbon emission indicators in Guangdong Province of China[J]. Ecological indicators: Integrating, monitoring, assessment and management,2020,115(Aug.):1-14.

[3] HEISEL, FELIX, MCGRANAHAN, JOSEPH, FERDINANDO, JOSEPH, et al. High-resolution combined building stock and building energy modeling to evaluate whole-life carbon emissions and saving potentials at the building and urban scale[J]. 2022,177.