基于Xgboost算法与Stacking组合模型的辽宁省碳排放预测研究  

Research on Carbon Emission Prediction in Liaoning Province Based on XGBoost Algorithm and Stacking Combination Model

作　　者：王城业 郭志达 Wang Chengye;Guo Zhida(School of Economics and Management,Dalian Jiaotong University,Dalian 116028,China)

机构地区：[1]大连交通大学经济管理学院,辽宁大连116028

出　　处：《环境科学与管理》2025年第4期17-22,共6页Environmental Science and Management

基　　金：国家社会科学基金重点项目(22AGJ007)。

摘　　要：随着全球气候变化问题的加剧,精确估算碳排放量成为制定有效环境政策及促进可持续发展的关键。本研究创新性地融合Xgboost算法与Stacking集成模型,运用先进的机器学习技术以优化碳排放预测。首先,利用Xgboost算法识别关键影响因素;随后,构建Stacking模型,该模型集成了多元线性回归、支持向量回归、极端梯度提升树及梯度提升决策树等多种方法,并以岭回归作为元学习器进行综合预测。实验结果显示,该模型展现出高度的预测精度与稳定性,为碳排放管理及治理策略提供了坚实的决策依据,对促进绿色低碳转型、实现碳中和目标具有重要意义。With the intensification of global climate change,accurate estimation of carbon emissions has become the key to formulating effective environmental policies and promoting sustainable development.This study integrates the Xgboost algorithm with the Stacking ensemble model,utilizing advanced machine learning techniques to optimize carbon emission predictions.Firstly,the Xgboost algorithm is used to to identify key influencing factors.Subsequently,a Stacking model was constructed,which integrates multiple methods such as multiple linear regression,support vector regression,extreme gradient boosting tree,and gradient boosting decision tree.A ridge regression is used as a meta learner for comprehensive prediction.The experimental results show that the model exhibits high prediction accuracy and stability,providing a solid decision-making basis for carbon emission management and governance strategies,which is of great significance for promoting green and low-carbon transformation and achieving carbon neutrality goals.

关 键 词：碳排放量预测 Xgboost算法 Stacking组合模型 机器学习 

分 类 号：X321[环境科学与工程—环境工程]