PM_(2.5) probabilistic forecasting system based on graph generative network with graph U-nets architecture

作     者：LI Yan-fei YANG Rui DUAN Zhu LIU Hui 李燕飞;杨睿;段铸;刘辉

作者机构：School of Mechatronic EngineeringHunan Agricultural UniversityChangsha 410128China Institute of Artificial Intelligence and Robotics(IAIR)Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075China 

出 版 物：《Journal of Central South University》 (中南大学学报(英文版))

年 卷 期：2025年第32卷第1期

页      面：304-318页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 070602[理学-大气物理学与大气环境] 0706[理学-大气科学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Project(2020YFC2008605)supported by the National Key Research and Development Project of China Project(52072412)supported by the National Natural Science Foundation of China Project(2021JJ30359)supported by the Natural Science Foundation of Hunan Province,China 

主　　题：PM_(2.5)interval forecasting graph generative network graph U-Nets sparse Bayesian regression kernel density estimation spatial-temporal characteristics 

摘      要：Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other *** the changes and trends of air pollution can provide a scientific basis for governance and prevention *** this paper,we propose an interval prediction method that considers the spatio-temporal characteristic information of PM_(2.5)signals from multiple stations.K-nearest neighbor(KNN)algorithm interpolates the lost signals in the process of collection,transmission,and storage to ensure the continuity of *** generative network(GGN)is used to process time-series meteorological data with complex *** graph U-Nets framework is introduced into the GGN model to enhance its controllability to the graph generation process,which is beneficial to improve the efficiency and robustness of the *** addition,sparse Bayesian regression is incorporated to improve the dimensional disaster defect of traditional kernel density estimation(KDE)interval *** the support of sparse strategy,sparse Bayesian regression kernel density estimation(SBR-KDE)is very efficient in processing high-dimensional large-scale *** PM_(2.5)data of spring,summer,autumn,and winter from 34 air quality monitoring sites in Beijing verified the accuracy,generalization,and superiority of the proposed model in interval prediction.