Duan Yonghui, Fan Yingying, Wang Xiang, Liu Kaige, Zhang Xiaotong
School of Civil Engineering, Henan University of Technology, Zhengzhou City, Henan Province, China.
School of Civil Engineering, Zhengzhou Aviation Industry Management College, Zhengzhou City, Henan Province, China.
PeerJ Comput Sci. 2025 Apr 17;11:e2827. doi: 10.7717/peerj-cs.2827. eCollection 2025.
As a central participant and important leader in the global climate governance system, China is facing the urgent need to predict and regulate the price of carbon emissions to promote the sound development of its carbon market. In this article, a rolling prediction model based on Least Absolute Shrinkage and Selection Operator-cheetah optimization algorithm-extreme gradient boosting (Lasso-COA-XGBoost) carbon price decomposition integration is proposed to address the defects of low prediction accuracy and insufficient model stability of a single machine learning model in the carbon price prediction problem. During the modeling process, the adaptive Lasso method is first employed to select factors from 15 primary indicators of carbon prices, identifying the most important influencing factors. Next, the COA-XGBoost model is built and the parameters of the XGBoost model are optimized using the COA algorithm. Finally, the complete ensemble empirical Mode Decomposition with adaptive noise (CEEMDAM) method is utilized to decompose the residual sequence of the COA-XGBoost model and reconstruct it into high-frequency and low-frequency components. Appropriate frequency models are applied to achieve error correction, thereby constructing the combined Lasso-COA-XGBoost-CEEMDAN model. To further enhance the predictive accuracy and practicality of the model, a rolling time window is introduced for forecasting in the Hubei and Guangzhou carbon emission trading markets, ensuring that the forecasting model can adapt to market changes in real-time. The experimental results show that, taking the carbon price prediction in Hubei as an example, the proposed hybrid model has a significant improvement in prediction accuracy compared with the comparison model (XGBoost model): the RMSE is improved by 99.9987%, the MAE is improved by 99.9039%, the MAPE is improved by 99.9960%, and the R is improved by 0.2004%, and the advantages of this hybrid model are also verified in other experiments. The results provide an effective experimental method for future carbon price prediction.
作为全球气候治理体系的核心参与者和重要领导者，中国迫切需要预测和调控碳排放价格，以推动碳市场的健康发展。本文提出一种基于最小绝对收缩和选择算子-猎豹优化算法-极端梯度提升（Lasso-COA-XGBoost）的碳价分解集成滚动预测模型，以解决单一机器学习模型在碳价预测问题中预测精度低和模型稳定性不足的缺陷。在建模过程中，首先采用自适应Lasso方法从15个碳价主要指标中筛选因素，确定最重要的影响因素。接着构建COA-XGBoost模型，并使用COA算法优化XGBoost模型的参数。最后，利用自适应噪声的完备总体经验模态分解（CEEMDAM）方法对COA-XGBoost模型的残差序列进行分解，并将其重构为高频和低频分量。应用合适的频率模型进行误差校正，从而构建组合的Lasso-COA-XGBoost-CEEMDAN模型。为进一步提高模型的预测精度和实用性，引入滚动时间窗口在湖北和广州碳排放交易市场进行预测，确保预测模型能够实时适应市场变化。实验结果表明，以湖北碳价预测为例，所提出的混合模型与对比模型（XGBoost模型）相比，预测精度有显著提高：均方根误差（RMSE）提高了99.9987%，平均绝对误差（MAE）提高了99.9039%，平均绝对百分比误差（MAPE）提高了99.9960%，相关系数（R）提高了0.2004%，并且该混合模型的优势在其他实验中也得到了验证。研究结果为未来碳价预测提供了一种有效的实验方法。
