基于Catboost模型的广东省近地面NO_(2)浓度估算  

Estimation of Near-surface NO_(2) Concentration in Guangdong Province Based on Catboost Model

作　　者：张洪飞 杜宁[1] 王莉[1] 张显云[1] 龚德才 李隆 ZHANG Hong-fei;DU Ning;WANG Li;ZHANG Xian-yun;GONG De-cai;LI Long(Mining College,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学矿业学院,贵阳550025

出　　处：《环境科学》2024年第11期6276-6285,共10页Environmental Science

基　　金：贵州省省级科技计划项目(黔科合支撑[2022]一般204)。

摘　　要：氮氧化物(NO_(x))是大气中的一类重要空气污染物,二氧化氮(NO_(2))是其主要组成部分之一,NO_(2)浓度的监测和估算对于环境保护和公共健康至关重要.使用Sentinel-5P大气污染监测卫星提供的近实时二氧化氮浓度数据(NRTI NO_(2))、ERA5气象再分析数据和DEM数据作为估算变量,基于Catboost模型,对广东省近地面NO_(2)浓度进行估算.结果表明:①Catboost模型估算的近地面NO_(2)浓度精度最高,其模型拟合的决定系数(R^(2))、均方根误差(RMSE)和平均绝对误差(MAE)分别达到0.91、4.89μg·m^(-3)和3.45μg·m^(-3),交叉验证R^(2)、RMSE和MAE分别达到0.90、4.91μg·m^(-3)和3.43μg·m^(-3),同时在月尺度和季尺度也具有良好的稳定性.②广东省近地面NO_(2)月均浓度总体上呈先降后升的“U”型趋势,1月的NO_(2)浓度最高,最高值为43.8μg·m^(-3),7月达到最低点,最低值为14.37μg·m^(-3).近地面NO_(2)季均浓度存在“冬高夏低,春秋过渡”的季节分布特征,各季节NO_(2)浓度大小依次为:冬季(27.53μg·m^(-3))>春季(20.77μg·m^(-3))>秋季(18.77μg·m^(-3))>夏季(14.85μg·m^(-3)).③从空间分布角度看,广东省近地面NO_(2)高值地区主要位于发展迅速且人口密集的地区,而低值地区主要分布在注重港口经济、农业和新能源等领域的地区.Nitrogen oxide(NO_(x))is an important air pollutant in the atmosphere,and nitrogen dioxide(NO_(2))is one of its main components.The monitoring and estimation of NO_(2) concentration is very important for environmental protection and public health.The near-real-time nitrogen dioxide concentration data(NRTI NO_(2)),ERA5 meteorological reanalysis data,and DEM data provided by Sentinel-5P atmospheric pollution monitoring satellite were used as estimation variables to estimate the near-surface NO_(2) concentration in Guangdong Province based on the Catboost model.The results showed that:①The Catboost model estimated the near-surface NO_(2) concentration with the highest accuracy,with the coefficient of determination(R^(2)),root mean square error(RMSE),and mean absolute error(MAE)of the model fit reaching 0.91,4.89µg·m^(-3),and 3.45µg·m^(-3)and the cross-validated R^(2),RMSE,and MAE reaching 0.90,4.91µg·m^(-3),and 3.43µg·m^(-3),with good stability on the monthly and quarterly scales.②The monthly average NO_(2) concentration near the surface of Guangdong Province showed a U-shaped trend,with the highest value of 43.8µg·m^(-3)in January and the lowest value of 14.37µg·m^(-3)in July.The seasonal distribution of the nearsurface NO_(2) concentration was characterized by“high during winter and low during summer and transitional during spring and autumn,”and the NO_(2) concentration in each season was in the following order:winter(27.53µg·m^(-3))>spring(20.77µg·m^(-3))>autumn(18.77µg·m^(-3))>summer(14.85µg·m^(-3)).③From a spatial distribution perspective,areas with high near-surface NO_(2) values in Guangdong Province were mainly located in rapidly developing and densely populated areas,while areas with low values were mainly distributed in areas focusing on port economy,agriculture,and new energy sources.

关 键 词：近地面NO_(2) Sentinel-5P 近实时二氧化氮 Catboost模型 时空分布 

分 类 号：X51[环境科学与工程—环境工程]