Prediction of energy‐related CO₂ emissions in multiple scenarios using a least square support vector machine optimized by improved bat algorithm: a case study of China

Abstract

At present, China has the world's highest CO2 emissions. The reduction of China's CO2 emissions will have a direct effect on the world. Considering that CO2 emissions mainly come from the burning of fossil fuel, it is of great significance to accurately calculate and forecast China's energy‐related CO2 emissions. To improve the prediction accuracy of CO2 emissions, this paper proposed a new prediction model, which combines t‐distribution, Gaussian perturbations bat algorithm, and a least squares support vector machine, namely the TBAG‐LSSVM model. Furthermore, in order to ensure the rationality of factor selection, a stationary test, cointegration test, and Granger causality test were utilized to analyze factors affecting CO2 emissions. Through an empirical test, it was found that the proposed model has higher accuracy than LSSVM, BA‐LSSVM, WOA‐LSSVM, ELM, and BPNN. Therefore, three scenarios were put into the model to predict China's CO2 emissions up to 2030. The results indicate that CO2 emissions in 2030 will be 12 853.18, 11 378.27, and 12 008.19 million tons. According to the simulation results, industrial restructuring and the elimination of outdated production capacity should be pushed forward continuously to ensure that the Chinese government achieves emission reduction targets. © 2019 Society of Chemical Industry and John Wiley & Sons, Ltd.

An aging giant at the center of global warming: Population dynamics and its effect on CO2 emissions in China

“…The detailed parameter settings are illustrated in Table 3. The growth rate of GDP and per-capita GDP in different scenarios refer to the estimates by scholars for the period 2021-2050 59,60 and China's 14th Five-Year Plan for the period 2021-2025. Regarding the annual decline rate of energy intensity, the rate in 2015 (3.93%/yr) was set for the BAU scenario as a reference.…”

Fuel Classification based on Flame Characteristics using a Time Series Analysis with Fuzzy Support Vector Machine Algorithm

“…Flame scanners are commonly used to operate burners and combustion systems in fossil fuel-fired utility boilers. 26 Flame scanners are fixed along with firing systems at different elevations in the boiler furnace to monitor flame stability. A signal from the flame scanner helps in managing the firing system for safe operations.…”

“…The main focus of those systems were to optimize the combustion process, classify flame images, monitor furnace flame, 23 find the temperature of natural gas and combustion flame, detect the unburnt carbons, predict the performance of refuse plastic fuel-fired boilers 19 and Proton Exchange Membrane fuel cells, 20 determine flame status in the burner, 4 combustion diagnosis and control system for burners and control the emission of N 2 O, NH 3 , SO 2, 24 CO, CO 2 , 25,26 NO X , 27 SO X , NO 2, CH 4 , HC, OH, C 2 , N 2, O 2, gases, ash and other pollutants, improve the boiler combustion quality, efficiency, [28][29][30][31] furnace, and boiler cost-effectiveness, 14,32 increase energy conservation, 23 and enhance the performance 33 and burner management. 34 Among those emissions, as mentioned before, some of the products are found as combustible.…”

A Review of Macroscopic Carbon Emission Prediction Model Based on Machine Learning

“…Random forest [42], Rough set theory [43], empirical mode decomposition [23,44], principal component analysis [45], Mean impact value method [46], Grey relational analysis [16,47,48], Bivariate correlation analysis [49], Generalized fisher index decomposition [50], Influence coefficient method [22] SVM Principal component analysis [19,29], Grey relational analysis [18,51,52], factor analysis [53], Detection of steady state [54], Cointegration test [54], Granger causality test [54][55][56], random forest [57], Impulse response function [58], Variance decomposition [58], Bivariate correlation analysis [19,29], Copula function [59], ridge regression analysis [32] LSTM Principal component analysis [33,60], Grey relational analysis [60], ensemble empirical mode decomposition [61], variational mode decomposition [61], multiple linear regression [33], regression analysis of quadratic assignment process [31], ARDL boundary test [17] RF Generalized additive models [62], Cluster analysis [63], random forest [63], Pearson test…”

“…Particle swarm optimization algorithm [22,42,48], genetic algorithm [16,69], Improved particle swarm optimization algorithm based on noninertial weight coefficient [49,50,70,71] SVM Particle swarm optimization algorithm [29,[72][73][74], Firefly Algorithm [26], FCS Algorithm [28], chicken swarm optimization algorithm [19], Fruit Fly Algorithm [53], Lion Optimizer [75], genetic algorithm [55,75], Grey Wolf Optimizer [76], Shuffled Frog Leaping Algorithm [51], Ocean Predator Algorithm [77], Bacterial Foraging Optimization Algorithm [52], Whale Optimization Algorithm [78], sparrow search algorithm [57], Gaussian perturbation bat algorithm [54], Butterfly Optimization Algorithm [19], Salp Swarm Algorithm [79] LSTM Bilstm [80], Attention-LSTM [81], sparrow search algorithm [31] RF…”