南京林业大学学报（自然科学版）2024，Vol.48Issue(3)：268-274,7.DOI:10.12302/j.issn.1000-2006.202205005
基于EMD和CatBoost算法的改进时间序列模型
Improved time series models based on EMD and CatBoost algorithms—taking PM2.5 prediction of Dalian City as an example
摘要
Abstract
[Objective]The study aims to address the problem of low accuracy in traditional PM2.5 concentration time series prediction,and to reduce the impact of nonlinearity,high noise,instability and volatility on the prediction of PM25 time series,to predict PM2.5 concentration more accurately.[Method]The haze PM25 data of Dalian City from January 1,2014 to January 31,2022 was used as an example.In this study,a hybrid machine learning time series model with the combination of empirical modal decomposition(EMD),classification boosting(CatBoost)and autoregressive integrated moving average model(ARIMA)was proposed.It was compared with the traditional autoregressive model(AR),ARIMA and the hybrid model with only the EMD method.[Result]The hybrid model EMD-CatBoost-ARIMA improved the root mean square error(RMSE)of the original sequence by 20.76％,the mean absolute error(MAE)by 17.40％,and the theil inequality coefficient(TIC)by 29.17％.[Conclusion]For reconstructed sequences with high entropy values,the EMD decomposition method and CatBoost algorithm can significantly improve the prediction performance of PM25 time series models.Compared with the traditional time series models,the EMD-CatBoost-ARIMA model has higher performance in PM2 5 concentration prediction.关键词
PM2.5浓度/经验模态分解(EMD)/时间序列模型/混合模型/CatBoost算法/机器学习/大连市Key words
PM25 concentration/empirical modal decomposition(EDM)/time series model/hybrid model/CatBoost algorithm/machine learning/Dalian City分类
资源环境引用本文复制引用
赵凌霄,李智扬,屈磊磊..基于EMD和CatBoost算法的改进时间序列模型[J].南京林业大学学报（自然科学版）,2024,48(3):268-274,7.基金项目
辽宁省博士科研启动基金项目(2020-BS-216) （2020-BS-216）
国家级大学生创新创业训练计划(202110158002) （202110158002）
辽宁省大学生创新创业训练计划(S202210158006). （S202210158006）
