Short-term impacts of air pollution on the platelet-lymphocyte ratio and neutrophil-lymphocyte ratio among urban adults in China

The short-term impacts of urban air pollution on the platelet-lymphocyte ratio (PLR) and neutrophil-lymphocyte ratio (NLR) remain obscure.In this study,we included 3487 urban adults from the Wuhan-Zhuhai cohort.Individual inhalation exposure to air pollutants was estimated by combining participants’daily breath volume and ambient concentrations of six air pollutants (includingfine particulate matter (PM_2.5),inhalable particulate matter(PM₁₀),nitrogen dioxide (NO₂...     

Design and demonstration of a next-generation air quality attainment assessment system for PM2.5 and O3

Due to the increasingly stringent standards, it is important to assess whether the proposed emission reduction will result in ambient concentrations that meet the standards. The Software for Model Attainment Test—Community Edition (SMAT-CE) is developed for demonstrating attainment of air quality standards of O₃ and PM_2.5. SMAT-CE improves computational efficiency and provides a number of advanced visualization and analytical functionalities on an integrated GIS platform. SMAT-CE incorporates historical measurements of air quality parameters and simulated air pollutant concentrations under a number of emission inventory scenarios to project the level of compliance to air quality standards in a targeted future year. An application case study of the software based on the U.S. National Ambient Air Quality Standards (NAAQS) shows that SMAT-CE is capable of demonstrating the air quality attainment of annual PM_2.5 and 8-hour O₃ for a proposed emission control policy.     

沈阳及周边城市大气细粒子的分布特征及其对空气质量的影响

利用沈阳、鞍山、抚顺和本溪4城市2007-2009年大气细粒子PM2.5及大气污染物PM10SO2、NO2的观测资料,分析了4城市大气细粒子的分布特征及其与空气质量的关系.结果表明:4城市大气细粒子PM2.5污染很重,年均浓度平均值超过美国大气细粒子PM2.5年均浓度标准4倍左右;4城市PM10、SO2的年均浓度呈下降...     

南昌市固定燃烧点源大气污染物排放清单及特征

大气污染物排放清单是了解区域污染物排放特征、准确模拟空气质量的重要资料,而工业点源是大气污染的重点排放源.通过收集相关活动水平信息和合理的排放因子,采用"自下而上"的方法建立了南昌市2014年点源大气污染物排放清单.结果表明,SO_2、NO_x、CO、PM_(10)、PM_(2.5)和VOC排放总量分别为29576.2、17115.1、25946.6、4689.4、922.9和1190.4 t,其中,金属炼制行业对SO_2、CO和VOC的贡献最高,分别占37.75%、30.59%和38.45%;火电行业是NO_x的主要来源,其贡献率为47%;水泥等建材制造行业对PM_(10)和PM_(2.5)排放贡献最高,分别为26%和25%.根据排放源污染物排放量及地理坐标信息,建立了0.4 km×0.4 km的污染物排放量空间分布特征图,结果表明,南昌市大气污染物排放较为集中,青山湖区北部和新建区北部是SO_2、NO_x、CO和VOC的主要排放区,而PM_(10)和PM_(2.5)的排放量相对分散,并在安义县出现排放高值区.通过将计算结果与统计数据结果进行对比,了解所估算清单的准确程度.对SO_2和NO_x的计算值和统计值进行统计分析,结果显示,NMB(标准化平均偏差)和NME(标准化平均误差)值均小于50%,清单计算精度较高.同时,为了解清单数据质量,对清单的不确定性进行定量分析,结果显示,SO_2和VOC不确定性较低而PM_(10)和PM_(2.5)的不确定性相对较高,清单整体不确定性与其他研究结果相差不大.建议后期研究可以从提升基础数据质量和建立具有区域代表性的排放因子数据库着手,从而减小排放量的不确定性,获得精准可靠的大气污染物清单并应用于空气质量模型预报等更深入的研究.     

Estimation of PM10 in the traffic-related atmosphere for three road types in Beijing and Guangzhou, China

The levels of roadside PM10 in Beijing, China, were investigated in 2011 and 2012 on a seasonal basis to estimate the population exposure to particulates for three road types. The measurements of PM10 were also conducted in the southern Chinese megacity of Guangzhou for comparison purposes. The results showed that roadside PMlo in Beijing correlated strongly with the PM10 background in the urban atmosphere. The levels of PM10 in street canyons were markedly higher than those along the open roads and in crossroad areas because of limited ventilation. An elevation of PM10 was observed in April, which was possibly due to the sand storms that frequently occur in the spring. Based on these observations, roadside PM10 in Beijing could have multiple origins and was to some extent dispersion- governed. In Guangzhou, the roadside PM10 did not closely relate to the background values. The PM10 pollution was greatly affected by local traffic conditions. The simulation of PM10 for different road types was completed during the study period using the Motor Vehicle Emissions Factor Model （MOBILE6.2） as an emission model and the California Line Source Dispersion Model （CALINE4） and Operational Street Pollution Model （OSPM） as dispersion models. The MOBILE6.2/CALINE4 software package was demonstrated to be sufficient for the simulation of PM10 in the open roads and crossroad areas in both Beijing and Guangzhou, and the simulation results of roadside PM10 in the street canyons by the MOBILE6.2/OSPM package were in close agreement with those of the measurements.     

深圳市2022年春季新冠疫情管控期间空气质量分析

短期减排是我国城市应对大气污染事件的重要应急管控手段,但短期减排的效益尚未得到完善分析.2022年3月14～20日,广东省深圳市为抑制新冠疫情传播实施了全市管控,为评估短期减排对华南城市春季空气质量的影响提供独特机会.结合深圳市高精度环境空气质量监测与气象观测等多源数据,分析了深圳市管控期间前后的空气质量变化.此次管控前和管控期中均有部分日期天气形势静稳,局地污染水平主要反映本地排放,有利于分析本地减排的影响.观测与WRF-GC区域化学模拟都表明,与珠三角周边城市相比,深圳市管控期间由于市内交通源排放显著减少,深圳市二氧化氮(NO₂)浓度降低(-26±9.5)%,可吸入颗粒物(PM₁₀)浓度降低(-28±6.4)%,细颗粒物(PM_2.5)浓度降低(-20±8.2)%,但臭氧(O₃)浓度无显著变化[(-1.0±6.5)%].TROPOMI卫星观测的甲醛和二氧化氮柱浓度数据对比表明,2022年春季珠三角臭氧光化学主要受挥发性有机物(VOCs)浓度控制,对氮氧化物浓度降低不敏感,反而可能因氮氧化物对臭氧滴...     

Moving towards ambitious climate policies: Monetised health benefits from improved air quality could offset mitigation costs in Europe

Air quality and related health effects are not only affected by policies directly addressed at air pollution but also by other environmental strategies such as climate mitigation. This study addresses how different climate policy pathways indirectly bear upon air pollution in terms of improved human health in Europe. To this end, we put in perspective mitigation costs and monetised health benefits of reducing PM_2.5 (particles less than 2.5 μm in diameter) and ozone concentrations.Air quality in Europe and related health impacts were assessed using a comprehensive modelling chain, based on global and regional climate and chemistry-transport models together with a health impact assessment tool. This allows capturing both the impact of climate policy on emissions of air pollutants and the geophysical impact of climate change on air quality.Results are presented for projections at the 2050 horizon, for a set of consistent air pollution and climate policy scenarios, combined with population data from the UN's World Population Prospects, and are expressed in terms of morbidity and mortality impacts of PM_2.5 and ozone pollution and their monetised damage equivalent.The analysis shows that enforcement of current European air quality policies would effectively reduce health impacts from PM_2.5 in Europe even in the absence of climate policies (life years lost from the exposure to PM_2.5 decrease by 78% between 2005 and 2050 in the reference scenario), while impacts for ozone depend on the ambition level of international climate policies. A move towards stringent climate policies on a global scale, in addition to limiting global warming, creates co-benefits in terms of reduced health impacts (68% decrease in life years lost from the exposure to PM_2.5 and 85% decrease in premature deaths from ozone in 2050 in the mitigation scenario relative to the reference scenario) and air pollution cost savings (77%) in Europe. These co-benefits are found to offset at least 85% of the additional cost of climate policy in this region.     

2014—2016年海口市空气质量概况及预报效果检验

本文主要基于CUACE模式在海口市的预报产品,结合2014年3月—2017年2月海口市AQI、PM_2.5、PM₁₀和O₃的实况资料进行预报效果检验.结果表明,①近3年海口市空气质量等级主要以优和良为主,但仍有少部分天数以PM₁₀、PM_2.5和O₃为首要污染物,分别占所有首要污染物天数的27.6%、29.5%和42.9%,其中O₃上升幅度较快.②CUACE模式能较好的模拟出AQI和3类污染物浓度的变化特征,其中PM_2.5的预报值与实测值最为接近,而PM₁₀和O₃普遍偏低.③日平均浓度的预报效果检验表明,PM_2.5的标准误差（RMSE）最小,AQI和PM₁₀次之,O₃最大.3个时次预报平均偏差（MB）和归一化偏差（MNB）均为负值,表明CUACE模式预报的污染要素浓度均偏低于实测值.④海口市空气质量为优等级时,TS评分最高;无首要污染物时,首要污染物预报的TS评分最高,但首要污染物为PM_2.5、PM₁₀或O₃时,TS评分均偏低.     

Application of AERMOD on near future air quality simulation under the latest national emission control policy of China：A case study on an industrial city

Air quality model can be an adequate tool for future air quality prediction, also atmospheric observations supporting and emission control strategies responders. The influence of emission control policy (emission reduction targets in the national "China’s 12th Five-Year Plan (2011-2015)") on the air quality in the near future over an important industrial city of China, Xuanwei in Yunnan Province, was studied by applying the AERMOD modeling system. First, our analysis demonstrated that the AERMOD modeling system could be used in the air quality simulation in the near future for SO2 and NOx under average meteorology but not for PM10. Second, after evaluating the simulation results in 2008 and 2015, ambient concentration of SO2, NOx and PM10 (only 2008) were all centered in the middle of simulation area where the emission sources concentrated, and it is probably because the air pollutions were source oriented. Last but not least, a better air quality condition will happen under the hypothesis that the average meteorological data can be used in near future simulation. However, there are still heavy polluted areas where ambient concentrations will exceed the air quality standard in near future. In spatial allocation, reduction effect of SO2 is more significant than NOx in 2015 as the contribution of SO2 from industry is more than NOx. These results inspired the regulatory applications of AERMOD modeling system in evaluating environmental pollutant control policy     

兰州市高分辨率人为源排放清单建立及在WRF-Chem中应用评估

城市尺度高分辨率人为源大气污染物排放清单是城市空气质量预报预警、污染成因分析和减排措施制定的重要基础数据,目前我国西部地区城市尺度的人为源排放清单研究仍然相对薄弱,能对接于空气质量模式的排放清单更为缺乏.本文整合已发表的清单文献,建立了可对接于空气质量模式的2016年兰州市城市尺度的人为源清单模型（HEI-LZ16）,将之应用于WRF-Chem模式,评估HEI-LZ16的准确性和适用性.结果表明：兰州市2016年人为源排放的SO₂、NO_x、CO、NH₃、VOCs、PM₁₀、PM_2.5、BC和OC总量分别为25642、53998、319003、10475、35289、49250、19822、2476和1482 t·a^-1.在模拟时间内,HEI-LZ16相比于MEIC,O₃和PM_2.5的NME值分别减小了140.2%和28.8%,HEI-LZ16更加准确适用.分析了HEI-LZ16情景下模拟的PM_2.5和O₃时空分布,兰州市臭氧MDA8呈现冬春季城区低而郊区高,夏秋季河谷城区西部及其下风向地区高的分布特征,夏秋季高浓度区的分布受偏东风和光化学反应的共同影响,冬季城区O₃浓度受NO_x排放的抑制作用浓度反而降低.PM_2.5浓度的高值区主要集中在黄河河谷盆地,本研究表明沿白银—兰州黄河河谷盆地走向的西侧存在一个污染物传输通道,其对兰州市环境空气质量具有较大的影响.     

Analysis and prediction of the influence of energy utilization on air quality in Beijing

This work evaluates the influence of energy consumption on the future air quality in Beijing, using 2000 as the base year and 2008 as the target year. It establishes the emission inventory of primary PM₁₀, SO₂ and NO_x related to energy utilization in eight areas of Beijing. The air quality model was adopted to simulate the temporal and spatial distribution of each pollutant concentration in the eight urban areas. Their emission, concentration distribution, and sectoral share responsibility rate were analyzed, and air quality in 2008 was predicted. The industrial sector contributed above 40% of primary PM₁₀ and SO₂ resulting from energy consumption, while vehicles accounted for about 65% of NO_x. According to the current policy and development trend, air quality in the eight urban areas could become better in 2008 when the average concentrations of primary PM₁₀, SO₂ and NO₂ related to energy utilization at each monitored site are predicted to be about 25, 50 and 51 μg/m³, respectively. Translated from China Environmental Science, 2005, 25(6): 746–750 [译自: 中国环境科学]     

Spatial and temporal variation of particulate matter and gaseous pollutants in 26 cities in China

O3and PM2.5were introduced into the newly revised air quality standard system in February 2012, representing a milestone in the history of air pollution control, and China's urban air quality will be evaluated using six factors(SO2, NO2, O3, CO, PM2.5and PM10) from the beginning of 2013. To achieve the new air quality standard, it is extremely important to have a primary understanding of the current pollution status in various cities. The spatial and temporal variations of the air pollutants were investigated in 26 pilot cities in China from August 2011 to February 2012, just before the new standard was executed. Hourly averaged SO2, NO2and PM10were observed in 26 cities, and the pollutants O3, CO and PM2.5were measured in 15 of the 26 cities. The concentrations of SO2and CO were much higher in the cities in north China than those in the south. As for O3and NO2, however, there was no significant diference between northern and southern cities. Fine particles were found to account for a large proportion of airborne particles, with the ratio of PM2.5to PM10ranging from 55% to 77%. The concentrations of PM2.5(57.5 μg/m3) and PM10(91.2 μg/m3) were much higher than the values(PM2.5: 11.2 μg/m3; PM10 : 35.6 μg/m3) recommended by the World Health Organization. The attainment of the new urban air quality standard in the investigated cities is decreased by 20% in comparison with the older standard without considering O3, CO and PM2.5, suggesting a great challenge in urban air quality improvement, and more eforts will to be taken to control air pollution in China.     

Impacts of pollution heterogeneity on population exposure in dense urban areas using ultra-fine resolution air quality data

Traditional air quality data have a spatial resolution of 1 km or above, making it challenging to resolve detailed air pollution exposure in complex urban areas. Combining urban morphology, dynamic traffic emission, regional and local meteorology, physicochemical transformations in air quality models using big data fusion technology, an ultra-fine resolution modeling system was developed to provide air quality data down to street level. Based on one-year ultra-fine resolution data, this study investigated the effects of pollution heterogeneity on the individual and population exposure to particulate matter (PM_2.5 and PM₁₀), nitrogen dioxide (NO₂), and ozone (O₃) in Hong Kong, one of the most densely populated and urbanized cities. Sharp fine-scale variabilities in air pollution were revealed within individual city blocks. Using traditional 1 km average to represent individual exposure resulted in a positively skewed deviation of up to 200% for high-end exposure individuals. Citizens were disproportionally affected by air pollution, with annual pollutant concentrations varied by factors of 2 to 5 among 452 District Council Constituency Areas (DCCAs) in Hong Kong, indicating great environmental inequities among the population. Unfavorable city planning resulted in a positive spatial coincidence between pollution and population, which increased public exposure to air pollutants by as large as 46% among districts in Hong Kong. Our results highlight the importance of ultra-fine pollutant data in quantifying the heterogeneity in pollution exposure in the dense urban area and the critical role of smart urban planning in reducing exposure inequities.     

基于PM2.5监测点空间聚类的关中五市空气污染区域识别

区域大气污染联防联控是空气质量管理的重要举措,准确识别空气污染区域对联防联控措施有重大意义.本研究采用陕西省关中五市（西安、咸阳、宝鸡、渭南、铜川）国控和省控全部90个监测点的小时级PM_2.5浓度监测数据,运用邻接约束层次聚类方法对监测点进行空间聚类,并利用泰森多边形和曲线平滑等技术识别空气污染区域.结果表明：1关中五市空气污染存在跨行政区划的区域性特征,本研究识别出2个特征显著不同的空气污染区域（区域1和区域2）;2区域2的PM_2.5浓度在统计上显著高于区域1,且重度和严重污染天数也显著高于区域1;3空气污染区域与地形特征关系密切,区域1均为高海拔区县,而区域2均为低海拔区县.依据空气污染区域的不同特征,在区域污染程度存在显著差异时,应当采取不同等级的污染防控措施,以减少对关中五市43%的国土面积、23个区县、639万人及3355亿元国内生产总值的影响,使区域空气污染防控措施更加科学、合理与精准.同时,空气污染区域的划分对缺失数据和不同空气污染等级表现稳健.     

Impact of energy structure adjustment on air quality: a case study in Beijing, China

Energy consumption is a major cause of air pollution in Beijing, and the adjustment of the energy structure is of strategic importance to the reduction of carbon intensity and the improvement of air quality. In this paper, we explored the future trend of energy structure adjustment in Beijing till 2020, designed five energy scenarios focusing on the fuel substitution in power plants and heating sectors, established emission inventories, and utilized the Mesoscale Modeling System Generation 5 (MM5) and the Models-3/Community Multiscale Air Quality Model (CMAQ) to evaluate the impact of these measures on air quality. By implementing this systematic energy structure adjustment, the emissions of PM₁₀, PM_2.5, SO₂, NO _x , and non-methane volatile organic compounds (NMVOCs) will decrease distinctly by 34.0%, 53.2%, 78.3%, 47.0%, and 30.6% respectively in the most coalintensive scenario of 2020 compared with 2005. Correspondingly, MM5-Models-3/CMAQ simulations indicate significant reduction in the concentrations of major pollutants, implying that energy structure adjustment can play an important role in improving Beijing’s air quality. By fuel substitution for power plants and heating boilers, PM₁₀, PM_2.5, SO₂, NO _x , and NMVOCs will be reduced further, but slightly by 1.7%, 4.5%, 11.4%, 13.5%, and 8.8% respectively in the least coal-intensive scenario. The air quality impacts of different scenarios in 2020 resemble each other, indicating that the potential of air quality improvement due to structure adjustment in power plants and heating sectors is limited. However, the CO₂ emission is 10.0% lower in the least coal-intensive scenario than in the most coal-intensive one, contributing to Beijing’s ambition to build a low carbon city. Except for energy structure adjustment, it is necessary to take further measures to ensure the attainment of air quality standards.     

兰-白城市群主要大气污染物网格化排放清单及来源贡献

甘肃兰-白城市群为我国西北地区重要的重工业基地,大气污染物排放总量较大.研究高空间分辨率的污染物排放清单对于区域空气质量预报预警、减排方案模拟研究及大气污染防治等具有重要的科学意义.本文以兰州和白银为主要研究区域,基于研究区域污染源排放及统计年鉴等数据资料,建立了兰（2015年）-白（2016年）城市群7种（类）主要大气污染物网格化排放清单,并对其空间排放特征以及排放源贡献进行了详尽地讨论分析.结果表明,兰-白城市群7种主要污染物年排放量分别为：NO_x 2.22×10⁵ t、NH₃ 4.53×10⁴ t、VOCs 7.74×10⁴ t、CO 5.62×10⁵ t、PM₁₀ 4.95×10⁵ t、PM_2.5 1.91×10⁵ t和SO₂ 1.37×10⁵ t.其中CO的排放量最大,NH₃的排放量最小.本清单与北大和清华MEIC清单对比结果表明,交通源排放3个清单一致性较高,CO排放总量和其工业源排放与北大和清华MEIC清单排放源相差30%~40%,推测原因主要为清单计算过程中排放因子、分辨率和数据年份的差异.本清单网格化空间分布显示除NH₃外的其他6种（类）污染物,排放主要集中在市区,排放源中工业非燃烧过程源均为最大贡献占比,NH₃的主要贡献源是氮肥的施用及禽畜排放,其污染分布受耕地分布等因素影响较大.因此,减少工业非燃烧过程源、整合优质高效电力供应、使用清洁能源、严格控制工地扬尘、工业粉尘和做好城区绿化等,能有效地降低兰-白城市群NO_x、VOCs、CO、PM₁₀、PM_2.5和SO₂这6种（类）主要污染物的排放.NH₃的减排则主要可从控制氮肥的使用及减少禽畜排放两方面考虑.本研究还利用蒙特卡洛法分析了排放清单的不确定性,NH₃的不确定性最大为-31%~30%,CO的不确定性最小为-18%~16%,清单整体可信度较高.     

利用多元线性回归方法评估气象条件和控制措施对APEC期间北京空气质量的影响

气象条件对大气污染物的扩散和传输有重要影响,准确分离和定量气象因素对空气质量的影响是评估大气污染控制政策有效性的前提.本研究利用APEC会议期间及前后(2014-10-15～2014-11-30)北京城区朝阳观测站点SO_2、NO、NO_2、NO_x、CO、PM_(2.5)、PM_1和PM_(10)以及气象因素的观测数据,采用多元线性回归分析方法,定量评估了气象条件和空气污染控制措施对APEC期间北京空气质量的影响.在假定排放条件不变的情况下,基于气象因素参数建立的预测污染物浓度的多元线性回归模型模拟效果较为理想,决定系数R~2在0. 494～0. 783之间.控制措施使得APEC控制期SO_2、NO、NO_2、NO_x、CO、PM_(2.5)、PM_1和PM_(10)浓度分别降低48. 3%、53. 5%、18. 7%、40. 6%、3. 6%、34. 8%、28. 8%和40. 6%,气象因素使得APEC控制期SO_2、NO、NO_2、NO_x、CO、PM_(2.5)、PM_1和PM_(10)浓度分别降低1. 7%、-2. 8%、18. 7%、4. 5%、18. 6%、27. 5%、30. 6%和35. 6%.气象因素和控制措施共同作用使得APEC控制期北京空气质量得到了明显改善.控制措施对SO_2和氮氧化物浓度的下降起主导作用,气象因素对CO浓度的下降起主导作用,气象因素和控制措施对颗粒物浓度降低的贡献相当.本研究还利用相对权重方法研究了气象因素对污染物浓度影响的贡献,结果表明影响不同污染物浓度的决定性气象因素不同.     

CMAQ模式及其修正技术在上海市PM_(2.5)预报中的应用检验

利用CMAQ空气质量数值预报模式对上海市PM2.5浓度进行预报,选取10个囯控站点监测数据对预报进行验证评估.结果表明,CMAQ模式开展能够较好地模拟出PM2.5的时间变化趋势及浓度水平,但总体处于低估的水平,偏低幅度约25%,尤其在高污染阶段,模式的低估更为突出,达32%,这与污染源清单的不确定性有关.为提高PM2.5预报准确度,采用学习型线性回归方法对PM2.5浓度的数值预报结果进行修正,统计检验结果显示修正预报准确率由原来的76.4%提高到了79.3%,污染预报成功指数由56.4%提高至72.1%,明显提高了PM2.5浓度的预报效果,反映了引入实际监测数据对空气质量数值预报模式进行修正的研究意义和可行性.     

A case study of development and application of a streamlined control and response modeling system for PM2.5 attainment assessment in China

This article describes the development and application of a streamlined air control and response modeling system with a novel response surface modeling-linear coupled fitting method and a new module to provide streamlined model data for PM_(2.5) attainment assessment in China.This method is capable of significantly reducing the dimensions required to establish a response surface model,as well as capturing more realistic response of PM_(2.5) to emission changes with a limited number of model simulations.The newly developed module establishes a data link between the system and the Software for Model Attainment Test—Community Edition(SMAT-CE),and has the ability to rapidly provide model responses to emission control scenarios for SMAT-CE using a simple interface.The performance of this streamlined system is demonstrated through a case study of the Yangtze River Delta(YRD) in China.Our results show that this system is capable of reproducing the Community Multi-Scale Air Quality(CMAQ) model simulation results with maximum mean normalized error 3.5%.It is also demonstrated that primary emissions make a major contribution to ambient levels of PM_(2.5) in January and August(e.g.,more than50%contributed by primary emissions in Shanghai),and Shanghai needs to have regional emission control both locally and in its neighboring provinces to meet China's annual PM_(2.5)National Ambient Air Quality Standard.The streamlined system provides a real-time control/response assessment to identify the contributions of major emission sources to ambient PM_(2.5)(and potentially O_3 as well) and streamline air quality data for SMAT-CE to perform attainment assessments.     

基于机器学习的成渝地区空气质量数值预报PM2.5订正方法研究

空气质量预报对于大气污染防治、打赢蓝天保卫战意义重大.本研究基于重庆市气象局的中尺度天气模式（WRF）和空气质量数值预报模式（CMAQ）的预报产品,采用2018年4个代表月份（1、4、7、10月,分别代表冬、春、夏和秋季）成渝地区22个观测站点的PM_2.5浓度和气象要素观测数据,建立基础特征变量数据集（包括训练数据集和测试数据集）,通过调整模型参数,并利用训练数据集采用机器学习方法（Lasso回归、随机森林回归、深度学习RNN-LSTM）进行模型训练,订正了成渝地区PM_2.5数值预报.其中,通过Lasso回归算法对成渝地区4个区域分别进行变量优选,优化模型,利用测试数据集对模型进行测试并检验评估.结果表明,基于3种机器学习方法订正后的PM_2.5小时浓度相比CMAQ模式模拟预报结果,偏差显著降低,相关系数显著提高.其中,随机森林回归和RNN-LSTM的订正效果优于Lasso回归,区域统计与站点统计结果较为一致;Lasso回归订正后的均方根误差减小50%左右,相关系数达70%,随机森林回归和RNN-LSTM订正后的均方根误差减小70%左右,相关系数达90%,随机森林回归与RNN-LSTM订正后的偏差范围相比Lasso回归集中范围更窄,最大概率分布更集中;3种方法对不同季节的订正效果与全年一致,其中,冬季订正效果更为显著.研究结果可为提高我国重点城市群区域—成渝地区PM_2.5浓度的大气污染预报能力提供有益参考.