昆明市碳排放预测与分析  

Prediction and Analysis of Carbon Emissions in Kunming City

作　　者：阚世朋 王辉涛[1] 赵玲玲 马裕翔 KAN Shipeng;WANG Huitao;ZHAO Lingling;MA Yuxiang(Faculty of Metallurgical and Energy Engineering,Kunming University of Science and Technology,Kunming 650093,China)

机构地区：[1]昆明理工大学冶金与能源工程学院,云南昆明650093

出　　处：《工业加热》2018年第4期32-35,共4页Industrial Heating

基　　金：国家自然科学基金(51366005)

摘　　要：基于灰色系统GM(1,1)预测方法。多元线性回归理论。BP神经网络预测方法,本文结合昆明市2000年~2015年碳排放量与其影响因素,建立BP神经网络预测模型。从预测结果可得,2020年昆明市单位GDP碳排放量较2005年单位GDP碳排放量下降73.81%~78.57%,三种预测结果中,BP神经网络预测的结果较为准确。在多元线性回归模型检验的结果中,得出影响昆明市碳排放量的因素从高到低依次为:人口、煤炭消费比率、能源强度、人均GDP、第三产业占比。Based on grey system GM(1,1)prediction method,multiple linear regression theory,BP neural network prediction method,com-bined with carbon emissions and its influencing factors from 2000 to 2015 in Kunming,the corresponding prediction model was established.The prediction results of three models available,the prediction accuracy of BP neural network is the highest,the unit GDP carbon emissions in 2020 decreased in the 73.81%~78.57%compared to 2005 in Kunming.Of the three prediction results,the results of BP neural network predic-tion are more accurate.In the result of multiple linear regression model tests,the influencing factors of carbon emissions in Kunming from high to low are:population,proportion of coal consumption,energy intensity,per capita GDP,proportion of third industries.Suggestions:decreas-ing moderately the growth rate of population,controlling the use of coal,developing renewable energy,developing actively the third industry.

关 键 词：碳排放 GM(1 1) 多元线性回归 BP神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]