中国建筑业碳排放影响因素与预测研究

Influencing Factors and Prediction of Carbon Emission in China’s Construction Industry

中国一直是碳排大国,其碳排放增长问题持续引发世界关注.建筑业作为一直在国民经济中占据重要地位的行业,其碳排放量约占全国碳排量的20%.因此,有必要研究建筑业碳排放的影响因素,并预测中国建筑碳排放的趋势.从以往相关研究中识别出12种我国建筑业碳排放影响因素,以2000—2016年的指标数据作为样本,利用灰色关联分析原理,筛选出关联度较高的8种影响因素,并结合BP神经网络模型构建我国建筑业碳排放预测模型.利用神经网络预测2017—2020年碳排放影响因素和碳排放预测值.研究发现,样本预测值对实际值的拟合度良好,说明所得训练网络泛化能力较强,进而证明筛选出的影响因素对建筑业碳排放影响程度高,可以用于预测建筑业碳排放.预测模型提高了神经网络的训练速度,为建筑业碳排放预测提供了新的工具.

China has always been the great power of carbon emission,and its carbon emission growth problem continues to attract world attention. As an industry that has always played an important role in the national economy,the construction industry accounts for about 20% of the country’s carbon emissions. Therefore,it is necessary to study the influencing factors of carbon emissions in the construction industry and predict the trend of carbon emissions in China’s construction. From the previous related research,12 factors affecting the carbon emission of China’s construction industry were identified. Using the index data of 2000-2016 as a sample,the gray correlation analysis principle was used to screen out eight influencing factors with high correlation. And combined with BP neural network, the network model constructs a carbon emission prediction model for China’s construction industry. We used neural networks to predict carbon emissions influencing factors and carbon emissions predictive value for 2017-2020. The study found that the sample predictive value has a good fit to the actual value,indicating that the training network has a strong generalization ability. It proves that the selected influencing factors have a high impact on the carbon emissions of the construction industry and can be used to predict the carbon emissions of the construction industry. The predictive model increases the training speed of the neural network and provides a new tool for building carbon emission prediction.