Prediction of aerosol optical depth in West Asia using deterministic models and machine learning algorithms

Nabavi, Seyed Omid; Haimberger, Leopold; Abbasi, Reyhaneh; Samimi, Cyrus

doi:10.1016/j.aeolia.2018.10.002

Cited by 30 publications

(15 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, machine learning provides the potential to understand past patterns of dust storms to predict future events. Many studies have applied machine learning algorithms to dust storm detection and prediction, including artificial neural network (ANN), support vector machine (SVM), random forests, CNN, logistic regression, and naïve Bayes (Kh Zamim et al, 2019;Lee et al, 2021;Nabavi et al, 2018).…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…The tools used for ground observation include video surveillance, observation towers, and remote sensors, such as radar or Lidar sensors. Dust storm prediction-related studies collect extensive data for about 10 years for specific cities, which is Geostationary Radiation Imager (AGRI) (Berndt et al, 2021;Chacon-murguía et al, 2011;Ebrahimi-khusfi, et al, 2021b;Ebrahimi-khusfi, et al, 2021a;El-ossta et al, 2013;Hou, Wu, et al, 2020;Lee et al, 2021;Ma et al, 2015;Nabavi et al, 2018;Qing-dao-er-ji et al, 2020;Rivasperea et al, 2015;Rivas-perea et al, 2010;Shahrisvand and Akhoondzadeh, 2013;Shi et al, 2020;Shi et al, 2019;Souri and Vajedian, 2015;Tiancheng et al, 2019;Wang et al, 2022;Xiao et al, 2015).…”

Section: Data Sourcesmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Applications to Dust Storms: A Meta-Analysis

Alshammari

Alrwais

Aksoy

2022

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

Dust storms are natural hazards that affect both people and properties. Therefore, it is important to mitigate their risks by implementing an early notification system. Different methods are used to predict dust storms, such as observing satellite images, analyzing meteorological data, and using numerical weather prediction model forecasts. However, recent studies have shown that machine learning algorithms have higher capacities to predict dust storms in less time and with fewer processing operations compared to numerical weather models. This paper conducted a meta-analysis review to examine studies that addressed the areas associated with the application of machine learning to dust storm prediction. It aims to compare the applied models and the types of data used in the literature under study. Given that the location of a dust storm event is essential, the properties of dust storms are discussed in relation to the region. The output classes and the various performance metrics observed in each reviewed paper are also summarized. Subsequently, the present paper offers a detailed analysis highlighting the capabilities of machine learning models in predicting dust storms. The analysis shows two main categories: early detection and dust storm prediction. Most models used for dust storm early detection from satellite images are support vector machines (SVM). In contrast, the most used models for dust storm prediction are SVM and random forests that predict the occurrence of dust storms from meteorological data. Finally, the paper highlights the challenges and future trends in the field, illustrating the potential directions for applying deep learning algorithms and providing longrange predictions with assessments of dust storm duration and intensity.

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

Section: Data Sourcesmentioning

confidence: 99%

Machine Learning Applications to Dust Storms: A Meta-Analysis

Alshammari

Alrwais

Aksoy

2022

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

show abstract

“…The structure of the NN model contains three components (input layer, two hidden layers, and output layer), as shown in the blue box of Figure 1. Previous studies mainly used some meteorological factors correlated with the evolution of atmospheric aerosol such as relative humidity, wind speed, surface pressure, and temperature [22,23,35,36]. Since the model targets are relative with the vertical variations of meteorological factors [21], it is necessary to add vertically changing factors (e.g., boundary layer height, vertical integral of temperature, and relative humidity at different altitudes) into the input dataset.…”

Section: Development Of the Prediction Modelmentioning

confidence: 99%

“…As for the complex nonlinear problems, neural network (NN) models can outperform most of traditional numerical models and empirical statistical methods [22]. Previous atmospheric aerosol studies have forecast the aerosol optical depth (AOD) [23] and some environmental parameters such as dust storm and PM 2.5 (respirable particulate matter with aerodynamic diameter below 2.5 mm) concentrations based on NN models [24][25][26]. Their results show that the NN models can well leverage the spatiotemporal correlations and reach a minimum error by training model, therefore, which can be adopted in the prediction on the vertical structures of absorbing aerosols.…”

Section: Introductionmentioning

confidence: 99%

Changes and Predictions of Vertical Distributions of Global Light-Absorbing Aerosols Based on CALIPSO Observation

Song

Bai

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Knowledge of the vertical distribution of absorbing aerosols is crucial for radiative forcing assessment, and its quasi real-time prediction is one of the keys for the atmospheric correction of satellite remote sensing. In this study, we investigated the seasonal and interannual changes of the vertical distribution of global absorbing aerosols based on satellite measurement from the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) and proposed a neural network (NN) model to predict the vertical distribution of global absorbing aerosols. Gaussian fitting was proposed to derive the maximum fitted particle number concentration (MFNC), altitude corresponding to MFNC (MFA), and standard deviation (MFASD) for vertical distribution of dust and smoke aerosols. Results showed that higher MFA values of dust and smoke aerosols mainly occurred over deserts and tropical savannas, respectively. For dust aerosol, the MFA is mainly observed at 0.5 to 6 km above deserts, and low MFNC values occur in boreal spring and winter while high values in summer and autumn. The MFA of smoke is systematically lower than that of dust, ranging from 0.5 to 3.5 km over tropical rainforest and grassland. Moreover, we found that the MFA of global dust and smoke had decreased by 2.7 m yr−1 (statistical significance p = 0.02) and 1.7 m yr−1 (p = 0.02) over 2007–2016, respectively. The MFNC of global dust has increased by 0.63 cm−3 yr−1 (p = 0.05), whereas that of smoke has decreased by 0.12 cm−3 yr−1 (p = 0.05). In addition, the determination coefficient (R2) of the established prediction models for vertical distributions of absorbing aerosols were larger than 0.76 with root mean square error (RMSE) less than 1.42 cm−3, which should be helpful for the radiative forcing evaluation and atmospheric correction of satellite remote sensing.

show abstract

“…The AOD is a common input that describes aerosol conditions in atmospheric transmission models, including the moderate resolution atmospheric transmission (MODTRAN) model (Berk et al 2011), which is developed and maintained by Spectral Sciences, Inc., and the Air Force Research Laboratory. MODTRAN uses AOD inputs to compute custom transmission spectra for atmospheric cross sections, and these inputs commonly come from sources such as AERONET, MERRA-2, or deterministic weather prediction models [e.g., the Weather Research and Forecasting Model coupled with Chemistry (WRF-Chem)] that can calculate AOD information as a component of short-term forecasts (Nabavi et al 2018). MODTRAN is an important transmission model that is widely used in applications pertinent to national security, including in modeling remote sensing and identifying transmission spectra for visible and infrared radiation transport.…”

Section: Introductionmentioning

confidence: 99%

Statistical Cluster Analysis of Global Aerosol Optical Depth for Simplified Atmospheric Modeling

Plymale,

Szekely,

Rubinstein

2022

Journal of Applied Meteorology and Climatology

View full text Add to dashboard Cite

Atmospheric aerosols originating from natural and anthropogenic sources have important implications for modeling atmospheric phenomena, but aerosol conditions can change significantly and rapidly because of their dependence on local geography and atmospheric conditions. In this work, we applied a computational k-means clustering algorithm to a global set of data obtained from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) to yield a set of 25 clusters that discriminate based on land type, elevation, and atmospheric conditions to predict statistical aerosol optical depth (AOD) information. We considered different subsets of MERRA-2 data, consisting of all the data averaged over a single year (2016) as well as data averaged by meteorological season over a span of five years (2012–2016), arriving at five separate sets of 25 clusters. We make the clustered AOD information available with decision trees, qualitative cluster descriptions, and color-coded cluster maps to assist in identifying which cluster to use in retrieving AOD information. The results of this analysis have applications in atmospheric modeling where knowledge of approximate or typical aerosol conditions are needed in lookup table form without requiring access to large atmospheric databases or computationally intensive aerosol models; such applications could include quick-turn or large volume analyses of atmospheric conditions required to inform decision-making impacting national security, such as in modeling remote sensing and estimating upper and lower bounds for visible and infrared photon transport.

show abstract

Prediction of aerosol optical depth in West Asia using deterministic models and machine learning algorithms

Cited by 30 publications

References 62 publications

Machine Learning Applications to Dust Storms: A Meta-Analysis

Machine Learning Applications to Dust Storms: A Meta-Analysis

Changes and Predictions of Vertical Distributions of Global Light-Absorbing Aerosols Based on CALIPSO Observation

Statistical Cluster Analysis of Global Aerosol Optical Depth for Simplified Atmospheric Modeling

Contact Info

Product

Resources

About