Forecasting carbon dioxide emissions: application of a novel two-stage procedure based on machine learning models. Issue 2 (1st February 2023)

• Record Type: Journal Article
• Authors: Wang, Chunzi; Li, Moye; Yan, Junpeng
• Is Part Of: Journal of water and climate change. Volume 14:Issue 2(2023)
• Page Start: 477
• Page End: 493
• Publication Date: 2023-02-01
• Subjects: artificial neural network -- CO2 emission forecast -- random forest -- ridge regression -- support vector regression -- two-stage forecast procedure; Water -- Periodicals; Hydrology -- Periodicals; Climatic changes -- Periodicals; Climatic changes; Hydrology; Water; Electronic journals; Periodicals; 333.9116
• DOI: 10.2166/wcc.2023.331
• Languages: English
• ISSNs: 2040-2244

Abstract

Abstract: Accurate forecast of carbon dioxide (CO2 ) emissions plays a significant role in China's carbon peaking and carbon neutrality policies. A novel two-stage forecast procedure based on support vector regression (SVR), random forest (RF), ridge regression (Ridge), and artificial neural network (ANN) is proposed and evaluated by comparing it with the single-stage forecast procedure. Nine independent variables' data (study period: 1985–2020) are used to forecast the CO2 emissions in China. Our results reveal that, when the time gap, h increases from 1 to 8, the average root mean squared error (RMSE) and mean absolute error (MAE) of SVR–SVR, SVR–RF, SVR–Ridge, and SVR–ANN are almost uniformly lower than errors arising from their single-stage version, respectively. Among these two-stage models, SVR–ANN exhibits the lowest forecast errors, whereas SVR–RF admits the highest. The mean percentage decrease in forecast errors of SVR–SVR vs. SVR, SVR–RF vs. RF, SVR–Ridge vs. Ridge, and SVR–ANN vs. ANN are 36.06, 5.98, 43.05, and 14.81 for RMSE, and 36.06, 6.91, 43.27, and 15.35 for MAE. Our two-stage procedure is also suitable to forecast other variables, such as fossil fuel and renewable energy consumption. HIGHLIGHTS: A novel two-stage forecast procedure is proposed and evaluated. Four hybrids of machine learning models based on SVR, RF, Ridge, and ANN are constructed to provide an accurate forecast of CO2 emissions in China. SVR–ANN gives the lowest forecast errors in terms of RMSE and MAE. SVR–Ridge shows the highest performance improvement than Ridge. Graphical Abstract