首页 | 本学科首页   官方微博 | 高级检索  
     

基于SVR的区域交通碳排放预测研究
引用本文:陈亮,王金泓,何涛,周志华,李巧茹,杨文伟. 基于SVR的区域交通碳排放预测研究[J]. 交通运输系统工程与信息, 2018, 18(2): 13-19
作者姓名:陈亮  王金泓  何涛  周志华  李巧茹  杨文伟
作者单位:1. 河北工业大学 土木与交通学院,天津 300401;2. 天津市绿色交通工程材料技术中心,天津 300401; 3. 广州市交通规划研究院,广州 510000
基金项目:国家自然科学基金/National Natural Science Foundation of China(51678212).
摘    要:基于STIRPAT模型,选择旅客周转量、货物周转量、人均GDP、机动车保有量、碳排放强度、能源结构和城市化率7项指标作为我国区域交通碳排放影响因素,建立基于支持向量回归机的碳排放预测模型,并以1990-2016年北京市交通碳排放相关数据为基础数据做实例分析.结果表明:训练样本交叉验证均方误差仅为 0.008 040,得到参数C和γ的最优值;模型预测值与真实值的拟合回归效果良好,训练集和测试集的相关系数分别为0.984 2和0.995 0,即模型具有良好的学习和推广能力;未来区域交通碳排放增长趋势逐渐变缓,但总量将继续呈上升趋势,社会仍然面临较大的温室气体减排压力.

关 键 词:综合交通运输  预测研究  SVR  交通碳排放  影响因素  
收稿时间:2017-09-14

Forecast Study of Regional Transportation Carbon Emissions Based on SVR
CHEN Liang,WANG Jin-hong,HE Tao,ZHOU Zhi-hua,LI Qiao-ru,YANG Wen-wei. Forecast Study of Regional Transportation Carbon Emissions Based on SVR[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(2): 13-19
Authors:CHEN Liang  WANG Jin-hong  HE Tao  ZHOU Zhi-hua  LI Qiao-ru  YANG Wen-wei
Affiliation:1. School of Civil and Transportation, Hebei University of Technology, Tianjin 300401, China; 2. Green Traffic Engineering Materials Technology Center of Tianjin, Tianjin 300401, China; 3. Guangzhou Transport Planning Research Institute, Guangzhou 510000, China
Abstract:Based on the STIRPAT model, seven influence factors are selected to build a forecasting model based on the SVR (support vector regression), including passenger-kilometers, freight ton-kilometers, per capita GDP, vehicle population, carbon intensity, energy structure and urbanization rate. Data of Beijing province from 1900 to 2016 is taken as an example for the case study. The results show that the optimal parameters of C and γ are gotten with the training samples’cross-validation mean square error of 0.008 040. With the correlation coefficients of 0.984 2 and 0.995 0, the SVR model had a good ability of learning and promotion. Although under a slowing growth trend of carbon emissions, the total transportation carbon emissions would continue to show an upward trend and the society is still faced with great pressure on the reduction of greenhouse gas emissions.
Keywords:integrated transportation  forecast study  SVR  transportation carbon emissions  influence factors  
本文献已被 CNKI 等数据库收录!
点击此处可从《交通运输系统工程与信息》浏览原始摘要信息
点击此处可从《交通运输系统工程与信息》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号