Forecasting of CO2 Emission in China, Using Least Squares Support Vector Machine Based on Improved Particle Swarm Optimization

Abstract

In recent years, a growing problem of haze issue has threatened human's survival and normal social economic sustainable development. In order to be able to find out the influence factors of China's carbon dioxide emissions more accurately, so as to adopt corresponding policies on energy conservation and emission reduction, an improved the least squares support vector machine optimized by improved particle swarm optimization algorithm (PSO-LSSVM) model for predicting carbon dioxide emissions in China was proposed in this paper, which can overcame the shortcomings of dependency in LSSVM model, which indicates that the IPSOLSSVM model established in this paper is more applicable to the current prediction of carbon emissions.