Response to Reviewer #1’s comments

The vertical distribution of aerosol extinction coefficient (EC) measured by lidar system has been used to retrieve the profile of particle matter with a diameter < 2.5 μm (PM2.5). However, the traditional linear model (LM) cannot consider the influence of multiple meteorological variables sufficiently, and then inducing the low inversion accuracy. Generally, the machine learning (ML) algorithms can input multiple features which may provide us with a new way to solve this constraint. 15 In this study, the surface aerosol EC and meteorological data from January 2014 to December 2017 were used to explore the conversion of aerosol EC to PM2.5 concentrations. Four ML algorithms were used to train the PM2.5 prediction models, including Random Forest (RF), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and eXtreme Gradient Boosting Decision Tree (XGB). The mean absolute error (root mean square error) of LM, RF, KNN, SVM and XGB models were 11.66 (15.68), 20 5.35 (7.96), 7.95 (11.54), 6.96 (11.18) and 5.62 (8.27) μg/m, respectively. This result show that the RF model is the most suitable model for PM2.5 inversions from EC and meteorological data. Moreover, the sensitivity analysis of model input parameters was also conducted. All these results further indicated that it is necessary to consider the effect of meteorological variables when using EC to retrieve PM2.5 concentrations. Finally, the diurnal and seasonal variations of transport flux (TF) and 25 PM2.5 profiles were analyzedanalysed based on the lidar data. The large PM2.5 concentration occurred

[1]  Xiao‐Ming Hu,et al.  Evaluation of WRF-Chem simulations on vertical profiles of PM2.5 with UAV observations during a haze pollution event , 2021 .

[2]  Fuchao Liu,et al.  Measurement report: characteristics of clear-day convective boundary layer and associated entrainment zone as observed by a ground-based polarization lidar over Wuhan (30.5° N, 114.4° E) , 2021 .

[3]  Fuchao Liu,et al.  Asian dust impacts on heterogeneous ice formation at Wuhan based on polarization lidar measurements , 2021 .

[4]  Wei Gong,et al.  Haze events at different levels in winters: A comprehensive study of meteorological factors, Aerosol characteristics and direct radiative forcing in megacities of north and central China , 2021 .

[5]  Jianguo Liu,et al.  Lidar vertical observation network and data assimilation reveal key processes driving the 3-D dynamic evolution of PM2.5 concentrations over the North China Plain , 2021, Atmospheric Chemistry and Physics.

[6]  Wei Gong,et al.  Adapting the Dark Target Algorithm to Advanced MERSI Sensor on the FengYun-3-D Satellite: Retrieval and Validation of Aerosol Optical Depth Over Land , 2021, IEEE Transactions on Geoscience and Remote Sensing.

[7]  H. Khalesifard,et al.  Monitoring atmospheric particulate matters using vertically resolved measurements of a polarization lidar, in-situ recordings and satellite data over Tehran, Iran , 2020, Scientific Reports.

[8]  Shihua Chen,et al.  Characteristics of aerosol within the nocturnal residual layer and its effects on surface PM2.5 over China , 2020 .

[9]  W. Gong,et al.  The characteristics and sources of the aerosols within the nocturnal residual layer over Wuhan, China , 2020 .

[10]  G. de Leeuw,et al.  Technical note: First comparison of wind observations from ESA's satellite mission Aeolus and ground-based radar wind profiler network of China , 2020, Atmospheric Chemistry and Physics.

[11]  Yuan Wang,et al.  Unexpected air pollution with marked emission reductions during the COVID-19 outbreak in China , 2020, Science.

[12]  S. Davis,et al.  Enhanced secondary pollution offset reduction of primary emissions during COVID-19 lockdown in China , 2020, National science review.

[13]  W. Paul Menzel,et al.  Retrieval of cloud top properties from advanced geostationary satellite imager measurements based on machine learning algorithms , 2020 .

[14]  W. Gong,et al.  Comparation of aerosol optical properties and associated radiative effects of air pollution events between summer and winter: A case study in January and July 2014 over Wuhan, Central China , 2019 .

[15]  Jianping Huang,et al.  Vertical distribution of PM2.5 and interactions with the atmospheric boundary layer during the development stage of a heavy haze pollution event. , 2019, The Science of the total environment.

[16]  Zhanqing Li,et al.  Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach , 2019, Remote Sensing of Environment.

[17]  Jianping Huang,et al.  Progress in Semi-arid Climate Change Studies in China , 2019, Advances in Atmospheric Sciences.

[18]  Yong Zhang,et al.  Boundary Layer Heights as Derived From Ground-Based Radar Wind Profiler in Beijing , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Kefei Zhang,et al.  Aerosol vertical distribution and sources estimation at a site of the Yangtze River Delta region of China , 2019, Atmospheric Research.

[20]  Ad Stoffelen,et al.  Characterizing ERA-Interim and ERA5 surface wind biases using ASCAT , 2019, Ocean Science.

[21]  L. Knibbs,et al.  A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information. , 2018, The Science of the total environment.

[22]  Wei Gong,et al.  Aerosol optical properties and radiative effects: Assessment of urban aerosols in central China using 10-year observations , 2018, Atmospheric Environment.

[23]  Zifa Wang,et al.  Air pollution over the North China Plain and its implication of regional transport: A new sight from the observed evidences. , 2018, Environmental pollution.

[24]  Zhenyi Chen,et al.  Vertical Distribution Characteristics of PM2.5 Observed by a Mobile Vehicle Lidar in Tianjin, China in 2016 , 2018, Journal of Meteorological Research.

[25]  Zhenyi Chen,et al.  Observations of particle extinction, PM 2.5 mass concentration profile and flux in north China based on mobile lidar technique , 2017 .

[26]  Liangpei Zhang,et al.  Estimating Ground‐Level PM2.5 by Fusing Satellite and Station Observations: A Geo‐Intelligent Deep Learning Approach , 2017, 1707.03558.

[27]  W. Gong,et al.  Observations of aerosol color ratio and depolarization ratio over Wuhan , 2017 .

[28]  Tong Zhu,et al.  Enhanced haze pollution by black carbon in megacities in China , 2016 .

[29]  Zhenzhu Wang,et al.  Profiling the PM 2.5 mass concentration vertical distribution in the boundary layer , 2015 .

[30]  Jinyuan Xin,et al.  Impact of emission controls on air quality in Beijing during APEC 2014: lidar ceilometer observations , 2015 .

[31]  Junying Sun,et al.  Observations of relative humidity effects on aerosol light scattering in the Yangtze River Delta of China , 2015 .

[32]  Zhanqing Li,et al.  Climate effects of dust aerosols over East Asian arid and semiarid regions , 2014 .

[33]  Jinyuan Xin,et al.  Observation of aerosol optical properties and particulate pollution at background station in the Pearl River Delta region , 2014 .

[34]  Huan Liu,et al.  Feasibility and difficulties of China's new air quality standard compliance: PRD case of PM 2.5 and ozone from 2010 to 2025 , 2013 .

[35]  Liangfu Chen,et al.  Satellite observation of abnormal yellow haze clouds over East China during summer agricultural burning season , 2013 .

[36]  Jen-Ping Chen,et al.  Interpreting aerosol lidar profiles to better estimate surface PM2.5 for columnar AOD measurements , 2013 .

[37]  F. Clavel-Chapelon,et al.  Adult asthma incidence and long term exposure to air pollution in six European cohorts: The European study of cohorts for air pollution effects (ESCAPE) , 2013 .

[38]  Andrew D. Foster,et al.  Satellite Remote Sensing for Developing Time and Space Resolved Estimates of Ambient Particulate in Cleveland, OH , 2011, Aerosol science and technology : the journal of the American Association for Aerosol Research.

[39]  Lijuan Cao,et al.  Support vector machines experts for time series forecasting , 2003, Neurocomputing.

[40]  J. Friedman.  Stochastic gradient boosting , 2002 .

[41]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[42]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[43]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[44]  F. G. Fernald.  Analysis of atmospheric lidar observations: some comments. , 1984, Applied optics.

[45]  M. L. Laucks,et al.  Aerosol Technology Properties, Behavior, and Measurement of Airborne Particles , 2000 .

[46]  W. Gong,et al.  Retrieving the Vertical Distribution of PM2.5 Mass Concentration From Lidar Via a Random Forest Model , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[47]  W. Gong,et al.  Study of continuous air pollution in winter over Wuhan based on ground-based and satellite observations , 2018 .

[48]  W. Gong,et al.  Surface Aerosol Optical Properties during High and Low Pollution Periods at an Urban Site in Central China , 2018 .

[49]  J. Léon,et al.  Impact of the mixing boundary layer on the relationship between PM2.5 and aerosol optical thickness , 2010 .

[50]  龚威,et al.  Measurements for profiles of aerosol extinction coefficient,backscatter coefficient,and lidar ratio over Wuhan in China with Raman/Mie lidar , 2010 .

[51]  L. Breiman.  Random Forests , 2001, Machine Learning.

[52]  D. Coomans,et al.  Alternative k-nearest neighbour rules in supervised pattern recognition : Part 1. k-Nearest neighbour classification by using alternative voting rules , 1982 .