Carbon emission prediction of construction industry in Sichuan Province based on the GA-BP model
Authors:
- 6 March 2024
- journal article
- research article
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 31 (16) , 24567-24583
Abstract
The reduction of the carbon emissions of construction industry is urgent. Therefore, it is essential to accurately predict the carbon emissions of the provincial construction industry, which can support differentiation emission reduction policies in China. This paper proposes a carbon emission prediction model that optimizes the backpropagation (BP) neural network by genetic algorithm (GA) to predict carbon emission of construction industry, or “GA-BP”. To begin with, the carbon emissions of construction industry in Sichuan Province from 2000 to 2020 are calculated by the emission factor method. Further, the electricity correction factor is introduced to eliminate the regional difference in electricity carbon emission coefficient. Finally, four factors are selected by the grey correlation analysis method to predict the carbon emission of construction industry in Sichuan Province from 2021 to 2025. The results show that the carbon emissions of construction industry in Sichuan Province have been trending up in the past two decades, with an average increase rate of 10.51%. The GA-BP model is a high-precision prediction model to predict carbon emissions of construction industry. The mean absolute percentage error (MAPE) of the model is only 6.303%, and its coefficient of determination is 0.853. Moreover, the carbon emissions of construction industry in Sichuan Province will reach 8891.97 million tons of CO2 in 2025. The GA-BP model can effectively predict the future carbon emissions of construction industry in Sichuan Province, which provides a new idea for the green and sustainable development of construction industry in Sichuan Province.Keywords
All Related Versions
This publication has 55 references indexed in Scilit:
- Carbon emission inequality and fairness from energy consumption by prefecture-level cities in ChinaEcological Indicators, 2023
- Can China achieve ecological sustainability? An LMDI analysis of ecological footprint and economic development decouplingEcological Indicators, 2023
- Emission accounting, sectoral contributions and gridded spatial distribution of greenhouse gases in a typical petrochemical district of ShanghaiAtmospheric Pollution Research, 2023
- Intelligent geometry compensation for additive manufactured oral maxillary stent by genetic algorithm and backpropagation networkComputers in Biology and Medicine, 2023
- The influencing factors of carbon emissions in the railway transportation industry based on extended LMDI decomposition method: evidence from the BRIC countriesEnvironmental Science and Pollution Research, 2022
- Study on spatio-temporal changes and driving factors of carbon emissions at the building operation stage- A case study of ChinaBuilding and Environment, 2022
- Method for the prediction of time series using small sets of experimental samplesApplied Mathematics and Computation, 2019
- Carbon emissions and policies in China's building and construction industry: Evidence from 1994 to 2012Building and Environment, 2016
- Scope-based carbon footprint analysis of U.S. residential and commercial buildings: An input–output hybrid life cycle assessment approachBuilding and Environment, 2014
- Input–output analysis of Irish construction sector greenhouse gas emissionsBuilding and Environment, 2010