Aerosol Classification Research Articles

Aerosol classification under non-clear sky conditions based on geostationary satellite FY-4A and machine learning models

Accurately identifying and classifying aerosols is a key to understanding their sources, assessing their chemical and physical changes, and comprehending their feedback mechanisms within climate system. However, existing aerosol classification methods have two limitations: First, ground remote sensing products have limited spatial coverage, and polar orbit satellite data suffer from low temporal resolution. Second, satellite-based aerosol classification methods are affected by cloud interference, resulting in data gaps. To overcome these challenges, this study utilized the extreme tree algorithm (ET) and integrated the FY-4A TOAR dataset with meteorological and geographical information, using a sequential forward selection method for optimal input feature selection. Focusing on the Asian region (70–140°E, 15–55°N), three models were used to generate hourly aerosol classification products: the Clear air-Cloud-Aerosol-Mixed cloud and aerosol (CCAM-ET) model, the Dust-Polluted dust-Other aerosols-Mixed aerosols (DPOM-ET) model under clear sky conditions, and the DPOM-ET model under non-clear sky conditions. The evaluated accuracy of the CCAM-ET model was 85%, demonstrating its effectiveness in identifying cloud and aerosol under various conditions. The CCAM model can achieve an accuracy of 78% when aerosols are located above clouds and 59% when they are below clouds. The DPOM-ET model achieved an evaluation accuracy of 89% for clear sky areas and 87% for non-clear sky areas, respectively, and was superior to traditional methods. Long-term data indicated a significant correlation between the distributions of different types of aerosols and human activity. Polluted dust is common in southwest China during spring and in northern China during winter. Additionally, from 2018 to 2020, dust occurrences decreased on the Indian Peninsula, while non-dust aerosols increased significantly in India and Southeast Asia.

Observation and Classification of Low-Altitude Haze Aerosols Using Fluorescence–Raman–Mie Polarization Lidar in Beijing during Spring 2024

Haze aerosols have a profound impact on air quality and pose serious health risks to the public. Due to its geographical location, Beijing experienced haze events in the spring of 2024. Lidar is an active remote sensing technology with a high spatiotemporal resolution and the ability to classify aerosols, and it is essential for effective haze monitoring. This study utilizes fluorescence–Raman–Mie polarization lidar with an emission wavelength of 355 nm, employing the δp-Gf method based on the particle depolarization ratio at 355 nm (δp355) and the fluorescence capacity (Gf), and combines meteorological data and backward-trajectory analysis to observe and classify low-altitude haze aerosols in Beijing during the spring of 2024. Notably, a mining dust event with strong fluorescence backscatter was detected. The haze aerosols were categorized into three types: pollution aerosols, desert dust, and mining dust. Their optical properties were summarized and compared. Desert dust showed a particle depolarization ratio range of 0.23–0.39 and a fluorescence capacity range from 0.18 × 10−4 to 0.63 × 10−4. Pollution aerosols had a larger fluorescence capacity but a lower depolarization ratio compared to desert dust, with a fluorescence capacity ranging from 0.55 × 10−4 to 1.10 × 10−4 and a depolarization ratio ranging from 0.10 to 0.17. Mining dust shared similar depolarization characteristics with desert dust but had a larger fluorescence capacity, ranging from 0.71 × 10−4 to 1.23 × 10−4, with a depolarization ratio range of 0.30–0.39. This study validates the effectiveness of the δp355-Gf method in classifying low-altitude haze aerosols in Beijing. Additionally, it offers a new perspective for more detailed dust classification using lidar. Furthermore, utilizing the δp355-Gf classification method and the δp355-Gf distributions of three typical aerosol samples, we developed a set of equations for the analysis of mixed aerosols. This method facilitates the separation and fraction analysis of aerosol components under various mixing scenarios. It enables the characterization of variations in the three types of haze aerosols at different altitudes and times, offering valuable insights into the interactions between desert dust, mining dust, and pollution aerosols in Beijing.

Long-Term Evaluation of Aerosol Optical Properties in the Levantine Region: A Comparative Analysis of AERONET and Aqua/MODIS

The focus on aerosol analysis in the Levantine Region is driven by climate-change impacts, the region’s increasing urban development and industrial activities, and its geographical proximity to major dust-source areas. This study conducts a comparative analysis of aerosol optical depth data from Aqua/MODIS and AERONET during different periods between 2003 and 2023 at four stations: IMS-METU-ERDEMLI (Mersin/Türkiye) (2004–2019), CUT-TEPAK (Limassol/Cyprus) (2010–2023), Cairo_EMA_2 (Cairo/Egypt) (2010–2023), and SEDE_BOKER (Sede Boker/Israel) (2003–2023). The objective is to evaluate the variability and reliability of AOD measurements between satellite and ground-based observations and to determine how well they represent regional climatology. The highest percentage of measurements within the expected error envelope was observed at the IMS-METU-ERDEMLI station, indicating the best agreement between MODIS and AERONET data at this location. The Seasonal-Trend Decomposition using Loess (STL) method revealed consistent spring and summer peaks influenced by dust transport from the Sahara and the Middle East, with lower values in winter. The study also considers the influence of cloud fraction on MODIS measurements and includes aerosol classification. A statistically significant slight positive trend in AOD values was identified at the IMS-METU-ERDEMLI station. Conversely, no significant trends were detected at the other stations. The results of this study agree with those of previous research on the impact of long-range dust transport on regional aerosol loadings, emphasizing the importance of integrating satellite and ground-based observations.

Uncertainties Assessment of Regional Aerosol Classification Schemes in South America

Uncertainties Assessment of Regional Aerosol Classification Schemes in South America

Leveraging Deep Learning as a New Approach to Layer Detection and Cloud–Aerosol Classification Using ICESat-2 Atmospheric Data

Leveraging Deep Learning as a New Approach to Layer Detection and Cloud–Aerosol Classification Using ICESat-2 Atmospheric Data

Temporal distributions of aerosols over the Horn of Africa–Ethiopia using MODIS satellite data: Part 01

There are large temporal variations in the optical properties and types of aerosols. These are due to the effects of environmental and meteorological conditions, industrial and agricultural influences, and other human influences and natural factors in each ecological functional area. Aerosol optical depth AOD and Ångström exponent AE parameters were extracted from the Moderate Resolution Imaging Spectroradiometer MODIS satellite with a 3 km resolution of MOD04_3K and MYD04_3K. The study covers sixteen selected stations in Horn Africa–Ethiopia with neighboring Eritrea, Djibouti, and South Sudan countries clustered into four regions for the periods of 2001–2022 to obtain detailed information on the temporal behaviors and classification of aerosols in each season. The results show that the temporal variability of AOD and AE values is large, with values ranging from 0.00 to 2.10 and 0.67 to 1.23, with minimum values most likely between December 16 and January 07, and maximum values between June 22 and July 24 for both Terra and Aqua in the southeast and northeast clusters, respectively. The lowest AOD and AE values were most common in the Belg (during September–November) and sometimes in Bega (during December–February), while the highest were in the Kiremt season (during June–August). The minimum values were observed at the Kebri Dahar site, and the maximum were at the Erta Ale site, which belongs to Ethiopia. Appropriate AOD and AE thresholds were used to classify the aerosol types into marine (MR), dust (DS), biomass burning (BB), desert dust (DD), urban (UR), and the residual cases were considered mixture (MX) types. The study concludes that marine aerosols were the most abundant at 47.71%, followed by urban aerosols at 28.29%, while desert dusts, enriched at 14.65%, accounted for the third place with free of dust particles. The Mann–Kendall (MK) statistical trend test was applied to the annual time series in all clustered regions and shows an almost positive increasing variability with a slight decrease in the forward series and vice–versa.

Consistency of Aerosol Optical Properties between MODIS Satellite Retrievals and AERONET over a 14-Year Period in Central–East Europe

Aerosols influence Earth’s climate by interacting with radiation and clouds. Remote sensing techniques aim to enhance our understanding of aerosol forcing using ground-based and satellite retrievals. Despite technological advancements, challenges persist in reducing uncertainties in satellite remote sensing. Our study examines retrieval biases in MODIS sensors on Terra and Aqua satellites compared to AERONET ground-based measurements. We assess their performance and the correlation with the AERONET aerosol optical depth (AOD) using 14 years of data (2010–2023) from 29 AERONET stations across 10 Central–East European countries. The results indicate discrepancies between MODIS Terra and Aqua retrievals: Terra overestimates the AOD at 16 AERONET stations, while Aqua underestimates the AOD at 21 stations. The examination of temporal biases in the AOD using the calculated estimated error (ER) between AERONET and MODIS retrievals reveals a notable seasonality in coincident retrievals. Both sensors show higher positive AOD biases against AERONET in spring and summer compared to fall and winter, with few ER values for Aqua indicating poor agreement with AERONET. Seasonal variations in correlation strength were noted, with significant improvements from winter to summer (from R2 of 0.58 in winter to R2 of 0.76 in summer for MODIS Terra and from R2 of 0.53 in winter to R2 of 0.74 in summer for MODIS Aqua). Over the fourteen-year period, monthly mean aerosol AOD trends indicate a decrease of −0.00027 from AERONET retrievals and negative monthly mean trends of the AOD from collocated MODIS Terra and Aqua retrievals of −0.00023 and −0.00025, respectively. An aerosol classification analysis showed that mixed aerosols comprised over 30% of the total aerosol composition, while polluted aerosols accounted for more than 22%, and continental aerosols contributed between 22% and 24%. The remaining 20% consists of biomass-burning, dust, and marine aerosols. Based on the aerosol classification method, we computed the bias between the AERONET AE and MODIS AE, which showed higher AE values for AERONET retrievals for a mixture of aerosols and biomass burning, while for marine aerosols, the MODIS AE was larger and for dust the results were inconclusive.

Global aerosol-type classification using a new hybrid algorithm and Aerosol Robotic Network data

Abstract. The properties of aerosols are highly uncertain owing to the complex changes in their composition in different regions. The radiative properties of different aerosol types differ considerably and are vital for studying aerosol regional and/or global climate effects. Traditional aerosol-type identification algorithms, generally based on cluster or empirical analysis methods, are often inaccurate and time-consuming. In response, our study aimed to develop a new aerosol-type classification model using an innovative hybrid algorithm to improve the precision and efficiency of aerosol-type identification. This novel algorithm incorporates an optical database, constructed using the Mie scattering model, and employs a random forest algorithm to classify different aerosol types based on the optical data from the database. The complex refractive index was used as a baseline to assess the performance of our hybrid algorithm against the traditional Gaussian kernel density clustering method for aerosol-type identification. The hybrid algorithm demonstrated impressive consistency rates of 90 %, 85 %, 84 %, 84 %, and 100 % for dust, mixed-coarse (mixed, course-mode aerosol), mixed-fine (mixed, fine-mode aerosol), urban/industrial, and biomass burning aerosols, respectively. Moreover, it achieved remarkable precision, with evaluation metric indexes for micro-precision, micro-recall, micro-F1-score, and accuracy of 95 %, 89 %, 91 %, and 89 %, respectively. Lastly, a global map of aerosol types was generated using the new hybrid algorithm to characterize aerosol types across the five continents. This study, utilizing a novel approach for the classification of aerosol, will help improve the accuracy of aerosol inversion and determine the sources of aerosol pollution.

Significant contribution of fractal morphology to aerosol light absorption in polluted environments dominated by black carbon (BC)

In recent years, researchers have emphasized the use of fractal aggregate morphology instead of the core-shell morphology in global climate models for estimating black carbon (BC) forcing. This study confirms that fractal morphology plays an important role in reducing the overestimation of aerosol light absorption calculations in the case of an urban polluted environment. During periods of high anthropogenic BC emissions at Delhi, the particle light absorption is overestimated by 50 to 200% by assumptions of both external mixing and internal core-shell mixing. While incorporating the aggregate morphology model into light absorption simulations is beneficial in such cases, it comes with a high computational burden. To address this, we propose a metric known as morphology index (MI). This index distributes the weightage between the two extreme cases of core-shell and fractal aggregate to obtain accurate particle light absorption. Long-range transported aerosols were estimated to have an MI of 0.78, and fresh local emissions had an MI of 0.48. A BC-based aerosol classification approach was developed to determine the most relevant particle size mode for light absorption. The method is based on patterns found between the correlations of the BC mass concentrations and aerosol number concentrations at the different particles sizes (BC-size correlation spectra). BC-size correlation spectra are introduced as a concept that may be used (i) independently to understand the size-dependent heterogeneous distribution of aerosol light absorption and (ii) in conjunction with MI to accurately model the optical properties of aerosols in different BC regimes.

Cloud–Aerosol Classification Based on the U-Net Model and Automatic Denoising CALIOP Data

Precise cloud and aerosol identification hold paramount importance for a thorough comprehension of atmospheric processes, enhancement of meteorological forecasts, and mitigation of climate change. This study devised an automatic denoising cloud–aerosol classification deep learning algorithm, successfully achieving cloud–aerosol identification in atmospheric vertical profiles utilizing CALIPSO L1 data. The algorithm primarily consists of two components: denoising and classification. The denoising task integrates an automatic denoising module that comprehensively assesses various methods, such as Gaussian filtering and bilateral filtering, automatically selecting the optimal denoising approach. The results indicated that bilateral filtering is more suitable for CALIPSO L1 data, yielding SNR, RMSE, and SSIM values of 4.229, 0.031, and 0.995, respectively. The classification task involves constructing the U-Net model, incorporating self-attention mechanisms, residual connections, and pyramid-pooling modules to enhance the model’s expressiveness and applicability. In comparison with various machine learning models, the U-Net model exhibited the best performance, with an accuracy of 0.95. Moreover, it demonstrated outstanding generalization capabilities, evaluated using the harmonic mean F1 value, which accounts for both precision and recall. It achieved F1 values of 0.90 and 0.97 for cloud and aerosol samples from the lidar profiles during the spring of 2019. The study endeavored to predict low-quality data in CALIPSO VFM using the U-Net model, revealing significant differences with a consistency of 0.23 for clouds and 0.28 for aerosols. Utilizing U-Net confidence and a 532 nm attenuated backscatter coefficient to validate medium- and low-quality predictions in two cases from 8 February 2019, the U-Net model was found to align more closely with the CALIPSO observational data and exhibited high confidence. Statistical comparisons of the predicted geographical distribution revealed specific patterns and regional characteristics in the distribution of clouds and aerosols, showcasing the U-Net model’s proficiency in identifying aerosols within cloud layers.

HETEAC-Flex: an optimal estimation method for aerosol typing based on lidar-derived intensive optical properties

Abstract. This study introduces a novel methodology for the characterization of atmospheric aerosol based on lidar-derived intensive optical properties. The proposed aerosol-typing scheme is based on the optimal estimation method (OEM) and allows the identification of up to four different aerosol components of an aerosol mixture, as well as the quantification of their contribution to the aerosol mixture in terms of relative volume. The four aerosol components considered in this typing scheme are associated with the most commonly observed aerosol particles in nature and are assumed to be physically separated from each other and, therefore, can create external mixtures. Two components represent absorbing and less-absorbing fine-mode particles, and the other two components represent spherical and non-spherical coarse-mode particles. These components reflect adequately the most frequently observed aerosol types in the atmosphere: combustion- and pollution-related aerosol, sea salt, and desert dust, respectively. In addition, to consolidate the calibration and validation efforts for the upcoming EarthCARE mission, the typing scheme proposed here is in accordance with the Hybrid End-To-End Aerosol Classification (HETEAC) model of EarthCARE. The lidar-derived optical parameters used in this typing scheme are the lidar ratio and the particle linear depolarization ratio at two distinct wavelengths (355 and 532 nm), the backscatter-related color ratio for the wavelength pair of 532/1064 nm and the extinction-related Ångström exponent for the wavelength pair of 355/532 nm. These intensive optical properties can be combined in different ways, making the methodology flexible, thus allowing its application to lidar systems with different configurations (e.g., single wavelength or multiwavelength, Raman, high spectral resolution). The typing scheme was therefore named HETEAC-Flex due to its compatibility with EarthCARE's HETEAC and its methodological flexibility. The functionality of the typing scheme is demonstrated by its application to three case studies based on layer-averaged optical properties.

Embedded Spatial–Temporal Convolutional Neural Network Based on Scattered Light Signals for Fire and Interferential Aerosol Classification

Photoelectric smoke detectors are the most cost-effective devices for very early warning fire alarms. However, due to the different light intensity response values of different kinds of fire smoke and interference from interferential aerosols, they have a high false-alarm rate, which limits their popularity in Chinese homes. To address these issues, an embedded spatial–temporal convolutional neural network (EST-CNN) model is proposed for real fire smoke identification and aerosol (fire smoke and interferential aerosols) classification. The EST-CNN consists of three modules, including information fusion, scattering feature extraction, and aerosol classification. Moreover, a two-dimensional spatial–temporal scattering (2D-TS) matrix is designed to fuse the scattered light intensities in different channels and adjacent time slices, which is the output of the information fusion module and the input for the scattering feature extraction module. The EST-CNN is trained and tested with experimental data measured on an established fire test platform using the developed dual-wavelength dual-angle photoelectric smoke detector. The optimal network parameters were selected through extensive experiments, resulting in an average classification accuracy of 98.96% for different aerosols, with only 67 kB network parameters. The experimental results demonstrate the feasibility of installing the designed EST-CNN model directly in existing commercial photoelectric smoke detectors to realize aerosol classification.

Classification of aerosols using particle linear depolarization ratio (PLDR) over seven urban locations of Asia

Active lidar remote sensing has been used to obtain detailed and quantitative information about the properties of aerosols. We have analyzed the spatio-temporal classification of aerosols using the parameters of particle linear depolarization ratio and single scattering albedo from Aerosol Robotic Network (AERONET) over seven megacities of Asia namely; Lahore, Karachi, Kanpur, Pune, Beijing, Osaka, and Bandung. We find that pollution aerosols dominate during the winter season in all the megacities. The concentrations, however, vary concerning the locations, i.e., 70–80% pollution aerosols are present over Lahore, 40–50% over Karachi, 90–95% over Kanpur and Pune, 60–70% and over Beijing and Osaka. Pure Dust (PD), Pollution Dominated Mixture (PDM), and Dust Dominated Mixture (DDM) are found to be dominant during spring and summer seasons.This proposes that dust over Asia normally exists as a mixture with pollution aerosols instead of pure form. We also find that black carbon (BC) dominated pollution aerosols.

Aerosol classification by application of machine learning spectral clustering algorithm

Precise understanding of aerosol classification is crucial for accurately quantifying the effects of aerosols on the Earth’s energy budget, improving remote sensing retrieval algorithms, formulating climate change-related policies, and more. In this study, we used aerosol measurements from the quality assured AERosol Robotic NETwork (AERONET) and utilized a multivariate spectral clustering algorithm, a machine learning tool, to classify global aerosols. The spectral clustering algorithm is a variant of the clustering algorithm that employs eigenvalues and eigenvectors of the data matrix to project the data into a lower-dimensional space of a similar cluster. To accomplish this, we considered five aerosol optical parameters: fine-mode Aerosol Optical Depth, Extinction Angstrom Exponent, Absorption Angstrom Exponent, Single Scattering Albedo, and Refractive Index from 150 AERONET sites distributed in six continents (Africa, Asia, Australia, Europe, North and South America) during 1993 to 2022. Using the clustering analysis, we identified four primary aerosol types: dust, urban, biomass burning, and mixed aerosols. Among the continents, the African and Asian sites exhibited the highest contribution of dust aerosols, as the region has significant global dust sources. Conversely, Australia, Europe, North, and South America are predominantly influenced by fine-mode aerosols, given their considerable distance from major dust source regions.

Distinct linear polarization of core-shell particles at near-backscattering directions.

The degree of linear polarization (-P12/P11) of scattered light by particles with a core-shell structure may display a distinct negative minimum at near-backscattering directions. However, the specific range of microphysical parameters within which this phenomenon occurs and the underlying physical mechanism are still unclear. Therefore, this study systematically investigated the impacts of particle size, shell-core ratio and refractive index on the negative minimum of -P12/P11 at near-backscattering angles for both coated spheres and coated super-spheroids. The findings reveal that the pronounced negative minimum at near-backscattering angles mostly appeared when the size parameter defined in terms of the mean radius was smaller than approximately 14.5 (e.g., the mean radius is smaller than approximately 2 μm at 0.865 µm wavelength) and the shell-core ratio was in a range of 1.4-1.9. The presence of weakly- and moderately-absorptive shells would lead to pronounced negative polarization at near backscattering directions. However, as the core absorption increased, the amplitude of negative minimum decreased and then stabilized. As for coated super-spheroids, the non-sphericity of the shell tended to suppress the negative polarization at near-backscattering directions. As a result, the pronounced negative minimum (<-0.4) mostly appeared when the aspect ratio and roundness of the shell were close to unity (the overall shape of the particle was nearly-spherical). However, the negative minimum of -P12/P11 showed little dependence on the shape of the core. Furthermore, the Debye series approach was employed to investigate the underlying mechanism of the negative minimum of -P12/P11 for coated spheres. The results demonstrated that the interference among the partial waves underwent one internal reflection on the shell-medium interface and, without internal reflection on the core-shell interface, led to the pronounced negative polarization at near-backscattering angles. When the core absorption was significant, the interference became negligible and the amplitude of the negative minimum was suppressed. This study enhances our understanding the scattering characteristic of coated particles and has implications in aerosol classification and polarized remote sensing.

Classification of Aerosols Types Over Iraq, using MODIS Date

The optical properties of aerosols are derived from Moderate Resolution Imaging Spectroradiometer (MODIS) observations for the period 2003–2021 at seventeen regions in Iraq, which were used to determine the different types of aerosols using threshold values based on Aerosols Optical Depth (AOD) and Angstrom Exponent (AE), seasonal aerosol classification was performed. This approach was verified and used in the detection process. Six aerosols categories: maritime, dust, mixture, urban, dust desert, and biomass burning were examined in this study. The result indicates that dust is most frequently detected in the summer and spring seasons, while the maritime type is most common in the winter and autumn, with wide variability in mixture type. The relative contribution during the winter months revealed a clear predominance of Maritime-type aerosols in the northern part of Iraq. Maximum contributions recorded in Erbil (93%), and Sulaymaniyah (90%). The maximum relative contributions of dust are found in the range of 71%–77% over Qaim and Haditha, while the southern regions of Iraq have a percentage ranging from 54%–65% in the summer season. The results of the monthly classification of aerosol type indicate that dust type are overhead maritime aerosols between March and September in the west, northwest, and south regions of Iraq. The highest contribution of desert dust was recorded in Basra, 60% during July and August. The maximum urban type was recorded at 50% in Baghdad in June. Biomass-burning type contribution was very little.

Composition and source based aerosol classification using machine learning algorithms

The aerosol particles present in the atmospheric region mainly affect the climate radiative forcing directly by scattering & absorbing the sunlight. Also, it indirectly influences the formation of clouds, precipitation and acts as a considerable uncertainty in assessing Earth's radiation budget. Determination of aerosol type is significant in characterizing the aerosol role in the atmospheric processes, feedback, and climate models. This paper proposes two aerosol classification models, one based on the source and another based on the composition, to classify the aerosols using aerosol optical properties. The source based aerosol classification method helps to identify the sources which cause pollution in a particular region. Based on the results, proper control measures can be taken to reduce pollution. The composition based aerosol classification helps to identify the nature of aerosol types, such as absorbing or non-absorbing. This classification helps to study the climate of the Kanpur region. The aerosol data is taken from AERONET (AErosol RObotic NETwork) for the period 2002–2018 for the Kanpur region. The composition based aerosol classification model uses Single Scattering Albedo (SSA), Angstrom Exponent (AE), and Fine Mode Fraction (FMF) parameters to categorize aerosols based on their composition. The source based aerosol classification model classifies the aerosols based on values of AE and Aerosol Optical Depth (AOD) and describes the source of the aerosol particles. Knowledge of aerosol sources and compositions helps execute policies or controls to reduce aerosol concentrations. Machine learning algorithms, Naïve Bayes, K Nearest Neighbor, Decision Tree, Support Vector Machine, and Random Forest are used to validate classification schemes. The performance analysis of machine learning algorithms is compared using ten different metrics, and the results are also compared with the existing aerosol classification models. The results of the classification show that the source based aerosols of the desert and arid background and the composition based aerosols of types, Mixture Absorbing, Coarse absorbing (Dust), and Black Carbon are dominant over the Kanpur region during the study period considered. The Number of non-absorbing (scattering) type aerosols are least in the study region considered during the study period at all the seasons. It is found that the Random Forest and Decision Tree models outperform the other machine learning models considered and the existing classification models in terms of accuracy (99.55 %) and other performance metrics considered.

Machine Learning Techniques for Vertical Lidar-Based Detection, Characterization, and Classification of Aerosols and Clouds: A Comprehensive Survey

This survey presents an in-depth analysis of machine learning techniques applied to lidar observations for the detection of aerosol and cloud optical, geometrical, and microphysical properties. Lidar technology, with its ability to probe the atmosphere at very high spatial and temporal resolution and measure backscattered signals, has become an invaluable tool for studying these atmospheric components. However, the complexity and diversity of lidar technology requires advanced data processing and analysis methods, where machine learning has emerged as a powerful approach. This survey focuses on the application of various machine learning techniques, including supervised and unsupervised learning algorithms and deep learning models, to extract meaningful information from lidar observations. These techniques enable the detection, classification, and characterization of aerosols and clouds by leveraging the rich features contained in lidar signals. In this article, an overview of the different machine learning architectures and algorithms employed in the field is provided, highlighting their strengths, limitations, and potential applications. Additionally, this survey examines the impact of machine learning techniques on improving the accuracy, efficiency, and robustness of aerosol and cloud real-time detection from lidar observations. By synthesizing the existing literature and providing critical insights, this survey serves as a valuable resource for researchers, practitioners, and students interested in the application of machine learning techniques to lidar technology. It not only summarizes current state-of-the-art methods but also identifies emerging trends, open challenges, and future research directions, with the aim of fostering advancements in this rapidly evolving field.

Variation of Aerosol Optical Properties over Cluj-Napoca, Romania, Based on 10 Years of AERONET Data and MODIS MAIAC AOD Product

Aerosols play an important role in Earth’s climate system, and thus long-time ground- based measurements of aerosol optical properties are useful in understanding this role. Ten years of quality-assured measurements between 2010 and 2020 are used to investigate the aerosol climatology in the Cluj-Napoca area, in North-Western Romania. In this study, we analyze the aerosol optical depth (AOD), single scattering albedo (SSA) and angstrom exponent obtained by the CIMEL sun photometer, part of the aerosol robotic network (AERONET), to extract the seasonality of aerosols in the region and investigate the aerosol climatology of the area. Higher aerosol loads are found during July and August. The angstrom exponent has the lowest values in April and May, and the highest in August. The classification of aerosols using AERONET data is performed to separate dust, biomass burning, polluted urban, marine and continental-dominant aerosol mixtures. In addition, the study presents the validation efforts of the Multi-Angle Implementation of Atmospheric Correction (MAIAC) dataset against AERONET AOD over a 10-year period.

The classification of atmospheric hydrometeors and aerosols from the EarthCARE radar and lidar: the A-TC, C-TC and AC-TC products

Abstract. The EarthCARE mission aims to probe the Earth's atmosphere by measuring cloud and aerosol profiles using its active instruments, the Cloud Profiling Radar (CPR) and ATmospheric LIDar (ATLID). The correct identification of hydrometeors and aerosols from atmospheric profiles is an important step in retrieving the properties of clouds, aerosols and precipitation. Ambiguities in the nature of atmospheric targets can be removed using the synergy of collocated radar and lidar measurements, which is based on the complementary spectral response of radar and lidar relative to atmospheric targets present in the profiles. The instruments are sensitive to different parts of the particle size distribution and provide independent but overlapping information in optical and microwave wavelengths. ATLID is sensitive to aerosols and small cloud particles, and CPR is sensitive to large ice particles, snowflakes and raindrops. It is therefore possible to better classify atmospheric targets when collocated radar and lidar measurements exist compared to using a single instrument. The cloud phase, precipitation and aerosol type within the column sampled by the two instruments can then be identified. ATLID-CPR target classification (AC-TC) is the product created for this purpose by combining the ATLID target classification (A-TC) and CPR target classification (C-TC). AC-TC is crucial for the subsequent synergistic retrieval of cloud, aerosol and precipitation properties. AC-TC builds upon previous target classifications using CloudSat and CALIPSO synergy while providing richer target classification using the enhanced capabilities of EarthCARE's instruments, specifically CPR's Doppler velocity measurements to distinguish snow and rimed snow from ice clouds and ATLID's lidar ratio measurements to objectively discriminate between different aerosol species and optically thin ice clouds. In this paper, we first describe how the single-instrument A-TC and C-TC products are derived from ATLID and CPR measurements. Then the AC-TC product, which combines the A-TC and C-TC classifications using a synergistic decision matrix, is presented. Simulated EarthCARE observations based on combined cloud-resolving and aerosol model data are used to test the processors generating the target classifications. Finally, the target classifications are evaluated by quantifying the fractions of ice and snow, liquid clouds, rain, and aerosols in the atmosphere that can be successfully identified by each instrument and their synergy. We show that radar–lidar synergy helps better detect ice and snow, with ATLID detecting radiatively important optically thin cirrus and cloud tops, while CPR penetrates most deep and highly concentrated ice clouds. The detection of rain and drizzle is entirely due to C-TC, while that of liquid clouds and aerosols is due to A-TC. The evaluation also shows that simple assumptions can be made to compensate for when the instruments are obscured by extinction (ATLID) or surface clutter and multiple scattering (CPR); this allows for the recovery of the majority of liquid cloud not detected by the active instruments.