基于随机森林模型的太原市夏季大气挥发性有机物分析
Analysis of Summer Atmospheric Volatile Organic Compounds in Taiyuan City Based on Random Forest Model
邵博 1崔阳 1何秋生 1郭利利1
作者信息
- 1. 太原科技大学 环境与资源学院,山西 太原 030024
- 折叠
摘要
当前,挥发性有机物(VOCs)作为O3 的重要前体物得到广泛关注,但对于解耦气象因素的VOCs真实排放情况了解有限.在太原市夏季O3 污染时期进行VOCs样品采集,研究期间VOCs体积分数均值为 30.6×10-9±9.3×10-9,平均温度为 26.7℃±3.3℃,光解速率(以NO2 代表,JNO2)日峰值为 9.2 s-1±1.0×10-3 s-1.为厘清人为排放和气象因素对VOCs的影响,使用基于机器学习的随机森林模型,量化去气象前后VOCs浓度变化.结果表明,气象归一化后TVOCs体积分数降幅为 0.4%,表明太原市夏季不利的气象条件导致TVOCs浓度增加.
Abstract
In recent years,volatile organic compounds(VOCs)have received extensive attention as an important precursor of O3,but the understanding of the real emission of VOCs that decouple meteorological factors is limited.In this case,VOCs samples were collected during the O3 pollution period in Taiyuan in summer.The average concentration of VOCs during the study period was 30.6×10-9±9.3×10-9,the average temperature was 26.7℃±3.3℃,and the daily peak of photolysis rate(represented by NO2,JNO2)was 9.2 s-1±1.0×10-3 s-1.In order to clarify the impact of anthropogenic emissions and meteorological factors on VOCs,a random forest model based on machine learning was used to quantify the changes in VOCs concentration before and after de-meteorology.The results showed that the concentration of TVOCs decreased by 0.4%after meteorological normalization,indicating that the unfavorable meteorological conditions in Taiyuan in summer led to the increase of TVOCs concentration.
关键词
O3/VOCs/随机森林模型/气象归一化Key words
O3/VOCs/random forest model/meteorological normalization引用本文复制引用
出版年
2024
NETL
NSTL
万方数据