Empirical assessment of carbon emissions in Guangdong Province within the framework of carbon peaking and carbon neutrality: a lasso-TPE-BP neural network approach

• Published in: Environmental science and pollution research international Vol. 30; no. 58; pp. 121647 - 121665
• Main Authors: Chen, Ruihan, Ye, Minhua, Li, Zhi, Ma, Zebin, Yang, Derong, Li, Sheng
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023; Springer Nature B.V
• Subjects: Algorithms; Aquatic Pollution; Atmospheric Protection/Air Quality Control/Air Pollution; Back propagation networks; Carbon; Carbon content; Carbon footprint; Carbon neutrality; Clean technology; Development strategies; Earth and Environmental Science; Economic development; Economics; Ecotoxicology; Emission analysis; Emissions; Emissions control; Empirical analysis; Energy conservation; Environment; Environmental accounting; Environmental Chemistry; Environmental Health; Environmental protection; Green development; Greenhouse gases; Neural networks; Population dynamics; Population number; Research Article; Statistical analysis; Sustainability reporting; Sustainable development; Waste Water Technology; Water Management; Water Pollution Control; Guangdong China; China; BP neural network; Lasso regression; Carbon neutrality; Tree-structured Parzen estimator; Scenario setting; Carbon peaking; Carbon emissions
• ISSN: 1614-7499; 0944-1344; 1614-7499
• DOI: 10.1007/s11356-023-30882-1

The escalating global greenhouse gas emission crisis necessitates a robust scientific carbon accounting framework and innovative development approaches. Achieving emission peaks remains the primary goal for emission reduction. Guangdong Province, a pivotal region in China, faces pressure to reduce carbon emissions. In this study, data was leveraged from the China Carbon Accounting Database (CEADS) and panel data from the “Guangdong Statistical Yearbook” spanning 1997 to 2022. Factors impacting carbon emissions were selected based on Guangdong Province’s carbon reduction goals, macroeconomic development strategies, and economic-population dynamics. To address multicollinearity, lasso regression identified key factors, including population size, economic development level, energy intensity, and technology factors. A novel STIRPAT extended model, combined with the BP neural network optimized using the TPE algorithm, enhanced carbon emission predictions for Guangdong Province. Employing scenario analysis, five scenarios were generated in alignment with the planning policies of Guangdong Province, to forecast carbon emissions from 2020 to 2050. The results suggest that to achieve a win-win situation for both economic development and environmental protection, Guangdong Province should prioritize the energy-saving scenario (S2), which aligns with the “13th Five-Year Plan’s” ecological and green development directives, to reach a projected carbon peak of 637.05Mt by 2030. In conclusion, recommendations for carbon reduction are proposed in the areas of low-carbon transformation for the population, sustainable economic development, and the development of low-carbon technologies.