气溶胶粒径吸湿增长因子的机器学习模型  

Machine learning models for aerosol particle size hygroscopic growth factor

作　　者：米家媛 李娜 佟景哲 倪长健[1] MI Jia-yuan;LI Na;TONG Jing-zhe;NI Chang-jian(College of Atmospheric Science,Chengdu University of Information Technology,Chengdu 610225,China;Liaoning Provincial Meteorological Equipment Support Center,Shenyang 110166,China)

机构地区：[1]成都信息工程大学大气科学学院,四川成都610225 [2]辽宁省气象装备保障中心,辽宁沈阳110166

出　　处：《中国环境科学》2024年第2期638-645,共8页China Environmental Science

基　　金：四川省科技厅应用基础研发项目(2021YJ0314);国家重点研发计划项目(2018YFC0214004,2018YFC1506006)。

摘　　要：利用成都市2017年10~12月浊度计、黑碳仪和GRIMM180环境颗粒物分析仪的逐时观测数据,结合该时段同时次大气能见度(V)、相对湿度(RH)和二氧化氮(NO_(2))监测资料,基于Mie散射理论和免疫进化算法反演气溶胶粒径吸湿增长因子.首先,以RH、C_(BC)、C_(BC)/C_(PM1)、C_(PM1)/C_(PM2.5)以及C_(PM2.5)/C_(PM10)作为解释变量集,构建了3种气溶胶粒径吸湿增长因子的机器学习模型(XGBoost模型、CatBoost模型和LightGBM模型),对应的决定系数(R 2)分别为0.869、0.893和0.898,均方根误差(RMSE)分别为0.108、0.097和0.090,平均绝对误差(MAE)分别为0.061、0.054和0.052.通过3种模型进行测试表明,气溶胶粒径吸湿增长的机器学习模型显著降低了传统单变量气溶胶粒径吸湿增长模型在高湿条件下的模拟偏差,也提升了气溶胶粒径吸湿增长多变量GAM模型的计算精度.最后,分析了不同解释变量对机器学习模型模拟效果的影响,确认了黑碳是气溶胶吸湿增长模型的主控变量.研究进一步阐明了气溶胶粒径吸湿增长因子多因素影响的复杂性,并为其模型的科学表征提供了新途径.Based on the hourly observational data of nephelometer,aethalometer and GRIMM180 environment particle monitor from October to December 2017 in Chengdu,as well as the simultaneous data of atmospheric visibility(V),relative humidity(RH)and nitrogen dioxide(NO_(2)),aerosol hygroscopic growth factor(Gf)was retrieved by the aid of Mie scattering theory and immune evolutionary algorithm.Firstly,RH,CBC,C_(BC)/C_(PM1),C_(PM1)/C_(PM2.5)and C_(PM2.5)/C_(PM10)were used as explanatory variables set,three machine learning models for aerosol particle size hygroscopic growth factors were constructed(XGBoost model,CatBoost model,and LightGBM model),and the corresponding judgment coefficients(R2)were 0.869,0.893 and 0.898,root mean square error(RMSE)were 0.108,0.097 and 0.090,mean absolute error(MAE)were 0.061,0.054 and 0.052,respectively.Tests of three models showed that,machine learning models for aerosol particle size hygroscopic growth significantly reduced the simulation bias of traditional univariate aerosol particle size hygroscopic growth models under high humidity conditions,and it also improved the calculation accuracy of multivariate GAM model for aerosol particle size hygroscopic growth.Finally,the effects on different explanatory variables of the simulation results of machine learning models were analyzed,black carbon was confirmed as the main control variable in the aerosol hygroscopic growth model.The above study further explained the complexity of the multifactorial influences on aerosol particle size hygroscopic growth factors,and provided a new approach to scientifically characterisation of Gf models.

关 键 词：气溶胶 粒径吸湿增长因子 机器学习 解释变量集 成都 

分 类 号：X513[环境科学与工程—环境工程]