BP神经网络和多元线性回归模型对碳排放预测的比较

为帮助钢铁企业了解自身的碳排放情况，更好的实现节能减排，建立BP神经网络和多元线性回归模型对钢铁企业碳排放进行预测分析，以期找到一种精确、实用的碳排放预测模型，为工业化生产提供参考依据，致力于帮助企业做好提前的碳排放预测，掌握自身排放情况，能够更有效的实施温室气体减排，将企业的碳排量控制在国家政策允许的范围内。结果表明：发现两种模型均能有效的对碳排放进行预测，误差均小于5%；BP神经网络模型对碳排放的预测优于多元线性回归模型。

Comparison of BP Neural Network and Multiple Linear Regression Models for Carbon Emissions Prediction

In order to help steel enterprises understand their carbon emissions and achieve better energy saving and emission reduction, BP neural network and multiple linear regression model are established to predict and analyze carbon emissions of steel enterprises, so as to find an accurate and practical carbon emission prediction model and provide a reference for industrial production. It is committed to helping enterprises to make carbon emission prediction in advance, grasp their own emissions, and more effectively implement greenhouse gas emission reduction, so as to control their carbon emission within the scope allowed by national policies. The results show that both models can effectively predict carbon emissions, and the error is less than 5%. BP neural network model is better than multiple linear regression model in predicting carbon emission.