基于机器学习的长治市PM_(2.5)和O_(3)污染影响因素研究  

Study on influencing factors of PM_(2.5)and O_(3)pollution in Changzhi based on machine learning

作　　者：贾瑞华 JIA Ruihua(Key Laboratory of Resource and Environmental System Optimization of Ministry of Education,College of Environmental Science and Engineering,North China Electric Power University,Beijing 102206,China)

机构地区：[1]华北电力大学环境科学与工程学院资源环境系统优化教育部重点实验室,北京102206

出　　处：《黑龙江环境通报》2025年第3期116-118,共3页Heilongjiang Environmental Journal

摘　　要：研究PM_(2.5)和O_(3)的污染特征,量化影响因素的贡献对于污染防治具有重要意义。本研究分析了2019—2022年的PM_(2.5)和O_(3)污染特征,并利用机器学习研究了PM_(2.5)和O_(3)污染影响因素。结果表明PM_(2.5)和O_(3)浓度整体均逐年降低,PM_(2.5)浓度受相对湿度和风速影响较大,日最高温度和太阳辐射对O_(3)影响较大,温度升高、太阳辐射增强易生成O_(3)。机器学习研究表明,不利的气象条件是秋冬季PM_(2.5)浓度较高的重要成因,春夏季的气象条件是造成O_(3)浓度较高的重要原因。It is of great significance to investigating the pollution characteristics of PM_(2.5)and O_(3),and quantifying the contributions of influencing factors for pollution prevention and control.This study analyzed the pollution characteristics of PM_(2.5)and O_(3)from 2019 to 2022,and employed the influencing factors of PM_(2.5)and O_(3)pollution by using machine learning techniques.The results showed that the overall concentrations of both PM_(2.5)and O_(3)have generally decreased year by year;the concentrations of PM_(2.5)were greatly affected by relative humidity and wind speed,whereas the daily maximum temperature and solar radiation have a greater impact on O_(3),and O_(3)was easy to be generated with rising temperature and enhanced solar radiation.The machine learning study showed that unfavourable meteorological conditions were an important cause of higher PM_(2.5)concentrations during the autumn and winter months,while meteorological conditions in the spring and summer were a key reason of higher O_(3)concentrations.

关 键 词：PM_(2.5) O_(3) 影响因素 气象贡献 机器学习 

分 类 号：X51[环境科学与工程—环境工程]