We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Analysis and forecast of China's carbon emission: evidence from generalized group method of data handling (g-GMDH) neural network.
- Authors
Bosah, C. P.; Li, S.; Mulashani, A. K.; Ampofo, G. K. M.
- Abstract
Achieving carbon emission targets requires an accurate analysis of trends in the rise and fall of carbon emissions. Due to economic growth and energy demand, China's emissions have increased dramatically in the past three decades. To this end, China has pledged to a carbon emissions peak by 2030, which has resulted in a large number of policy initiatives to cut emissions. Therefore, this study aims to present the generalized structure of machine learning (ML) derived group method of data handling (g-GMDH) as an improved alternative for analyzing and predicting China's future CO2 emission trends. The study used annual data from 1980 to 2019 for gross domestic product, total natural resource rent, industrialization, urbanization, renewable energy, and non-renewable energy consumption to forecast the CO2 emissions trend from 2020 to 2043. The CO2 prediction results indicate that China will reach its CO2 emission peak in 2033. Sensitivity analysis results revealed that industrialization, non-renewable energy, and urbanization significantly impacted the model's output and contributed the most to CO2 emissions. In contrast, renewable energy consumption contributed the least to CO2 emissions. The findings of this study can provide valuable guidelines for decision-makers as they set CO2 reduction goals and implement appropriate energy-saving and emission-reduction initiatives.
- Subjects
CHINA; CARBON emissions; ENERGY consumption forecasting; NATURAL resources; INPUT-output analysis; GREENHOUSE gas mitigation; MACHINE learning; GROSS domestic product; CARBON offsetting
- Publication
International Journal of Environmental Science & Technology (IJEST), 2024, Vol 21, Issue 2, p1467
- ISSN
1735-1472
- Publication type
Article
- DOI
10.1007/s13762-023-05043-z