王娟,李学鹏

• 1:铜仁学院大数据学院
• 2:铜仁学院材料与化学工程学院

摘要(Abstract)：

精准有效地预测碳排放量有助于推动低碳经济的发展。基于2000—2023年时间序列数据，选取国内生产总值（gross domestic product, GDP）、能源消耗、城镇化水平和人口数量等核心驱动因素作为预测指标，分别构建灰色模型（grey model, GM）GM(1,5)、反向传播神经网络（back propagation neural network, BPNN）模型和岭回归模型（ridge regression model, RRM）进行实证分析。实证分析结果表明，3种单一模型的平均相对误差（mean relative error, MRE）分别为5.06%、0.44%和1.02%。为进一步提升预测精度，采用误差倒数法确定最优权重系数，构建了GM-BPNN-RRM变权组合预测模型。结果显示，组合模型的平均相对误差降至0.40%，其预测性能优于各单一模型。

关键词(KeyWords)： GM(1,5);反向传播神经网络;岭回归模型;误差倒数法;变权组合模型

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 王娟,李学鹏

DOI: 10.16508/j.cnki.11-5866/n.2025.05.012

参考文献(References)：

• [1]黄昕怡，吴嘉仪，林文浩，等.基于GM(1,1)模型的江苏省碳排放预测[J].黑龙江科学，2022,13(18):26-28.HUANG X Y,WU J Y,LIN W H,et al. Forecast of carbon emission of Jiangsu province based on GM(1,1)model[J].Heilongjiang Science,2022,13(18):26-28.(in Chinese)
• [2] TANG D C,MA T Y,LI Z J,et al. Trend prediction and decomposed driving factors of carbon emissions in Jiangsu province during 2015—2020[J]. Sustainability,2016,8(10):1018.
• [3]吴小洁.改进的多变量灰色模型及其在碳排放预测中的应用[D].南京：南京信息工程大学，2023.WU X J. An improved multivariate grey model and its application in carbon emission forecasting[D]. Nanjing:Nanjing University of Information Science&Technology,2023.(in Chinese)
• [4]阳建中，陈慧蓉，刘志先，等.信息熵和多因素灰色系统模型在碳排放的分析与预测[J].中南民族大学学报（自然科学版），2022,41(1):123-128.YANG J Z,CHEN H R,LIU Z X,et al. Information entropy and multi-factors grey system model in carbon emission analysis and forecasting[J]. Journal of South-Central Minzu University(Natural Science Edition),2022,41(1):123-128.(in Chinese)
• [5] WEN L, YUAN X Y. Forecasting CO2 emissions in Chinas commercial department, through BP neural network based on random forest and PSO[J]. Science of the Total Environment,2020,718:137194.
• [6]赵金元，马振，唐海亮. BP神经网络和多元线性回归模型对碳排放预测的比较[J].科技和产业，2020,20(11):172-176.ZHAO J Y,MA Z,TANG H L. Comparison of BP neural network and multiple linear regression models for carbon emissions prediction[J]. Science Technology and Industry,2020,20(11):172-176.(in Chinese)
• [7]李雨，王君，张萌萌，等.基于PSO-BP模型的省域交通运输碳排放多情景预测[J].华南师范大学学报（自然科学版），2025,57(2):12-22.LI Y,WANG J,ZHANG M M,et al. Multi-scenario prediction of provincial transportation carbon emissions using the PSO-BP model[J]. Journal of South China Normal University(Natural Science Edition),2025,57(2):12-22.(in Chinese)
• [8]刘东君，邹志红.最优加权组合预测法在水质预测中的应用研究[J].环境科学学报，2012,32(12):3128-3132.LIU D J,ZOU Z H. Application of weighted combination model on forecasting water quality[J]. Acta Scientiae Circumstantiae,2012,32(12):3128-3132.(in Chinese)
• [9]吕欣曼，殷克东，李雪梅.灰色多元变权组合预测模型及其应用[J].统计与决策，2022,38(14):25-29.LüX M,YIN K D,LI X M. Grey multivariate variable weight combination prediction model and its application[J]. Statistics and Decision,2022,38(14):25-29.(in Chinese)
• [10]张恒.基于变权组合模型的碳排放量预测[J].现代信息科技，2024,8(22):122-126.ZHANG H. Carbon emission prediction based on variable weight combination model[J]. Modern Information Technology,2024,8(22):122-126.(in Chinese)
• [11]张鹏.组合预测中变权与定权的应用比较[J].统计与决策，2018,34(17):80-82.ZHANG P. Comparison of time-varying and fixed weights in combination forecasting[J]. Statistics and Decision,2018,34(17):80-82.(in Chinese)