The Frontiers of Society, Science and Technology, 2024, 6(9); doi: 10.25236/FSST.2024.060909.
Shasha Xiong, Xinyi Zhang, Bo Yang
College of Economics and Management, Qinghai Normal University, Xining City, Qinghai Province, 810008, China
This study aims to predict carbon emissions in Qinghai Province using advanced machine learning techniques to aid in achieving sustainable development goals. A "top-down" carbon emission calculation model was developed, revealing that the carbon emissions from Qinghai's transportation sector increased significantly from 2004 to 2022. To further analyze the influencing factors, an improved STIRPAT model was constructed, taking into account variables such as population, economic growth, energy consumption, and transportation development. The study also employed a Long Short-Term Memory (LSTM) neural network for prediction, comparing its performance with other models such as BP neural network and Support Vector Machines (SVM). The results show that the LSTM model achieved the best predictive accuracy, indicating that Qinghai's carbon emissions will peak around 2036. This research provides valuable insights into carbon emission dynamics and offers practical guidance for policy-making and environmental management in the region.
Carbon Emissions, Machine Learning, STIRPAT Model, LSTM, Qinghai Province
Shasha Xiong, Xinyi Zhang, Bo Yang. Research on Carbon Emission Prediction of Qinghai Province Based on Machine Learning. The Frontiers of Society, Science and Technology (2024), Vol. 6, Issue 9: 52-58. https://doi.org/10.25236/FSST.2024.060909.
[1] Wang X. N., Gu K. P. "Research on the Current Situation of Carbon Source Emission Estimation Methods in China" [J]. Environmental Science and Management, 2006, 31(4): 78-80.
[2] Liu Z., Guan D., Wei W., et al. "Reduced Carbon Emission Estimates from Fossil Fuel Combustion and Cement Production in China" [J]. Nature, 2015, 524(7565): 335-338.
[3] Wang M., Zhou Z. X., Feng M. M., et al. "CO2 Emission Monitoring Model and Accuracy Verification of Thermal Power Units Using Direct Measurement Method" [J]. Coal Chemical Industry, 2022, 50(02): 18-21+33.
[4] Qin Z., Zhang J. E., Luo S. M., Ye Y. Q. "System Dynamics Prediction of Energy Consumption and CO2 Emissions in China" [J]. Chinese Journal of Eco-Agriculture, 2008, 66(04): 1043-1047.
[5] Chen B., Yang W. S. "Research on the Carbon Emission Accounting Method of Industrial Parks" [J]. China Population, Resources and Environment, 2017, 27(03): 1-10.
[6] Deng G. Y., Ma R., Zhang Z. J. "Decomposition Study on the Carbon Emission Effect of Energy Consumption in Various Industries in China" [J]. Statistics and Decision, 2018, 34(15): 124-127.