Faced with serious growing global warming problem, it is important to predict carbon emissions. As there are a lot of factors affecting carbon emissions, a novel multi-variable grey model (GM(1,N) model) based on linear time-varying parameters discrete grey model (TDGM(1,N)) has been established. In this model, linear time-varying function is introduced into the traditional model, and dynamic optimization of fixed parameters which can only be used for static analysis is carried out. In order to prove the applicability and effectiveness of the model, this paper compared the model with the traditional model and simulated the carbon emissions of Anhui Province from 2005 to 2015. Carbon emissions in the next two years are also predicted. The results show that the TDGM(1,N) model has better simulation effect and higher prediction accuracy than the traditional GM(1,N) model and the multiple regression model(MRM) in practical application of carbon emissions prediction. In addition, the novel model of this paper is also used to predict the carbon emissions in 2018–2020 of Anhui Province.

中文翻译：

---

使用基于线性时变参数的多变量 GM (1,N) 模型预测碳排放

面对日益严重的全球变暖问题，预测碳排放非常重要。由于影响碳排放的因素较多，基于线性时变参数离散灰色模型(TDGM(1,N))建立了一种新型的多变量灰色模型(GM(1,N)模型)。该模型在传统模型中引入线性时变函数，对只能用于静力分析的固定参数进行动态优化。为验证模型的适用性和有效性，本文将模型与传统模型进行对比，对安徽省2005-2015年的碳排放进行了模拟，并对未来两年的碳排放进行了预测。结果表明，TDGM(1, N)模型在碳排放预测的实际应用中比传统的GM(1,N)模型和多元回归模型(MRM)具有更好的模拟效果和更高的预测精度。此外，本文的新模型还用于预测安徽省2018-2020年的碳排放。