Direct aerosol optical depth retrievals using MODIS reflectance data and machine learning over East Asia

Kang, Eunjin; Park, Seonyoung; Kim, Miae; Yoo, Cheolhee; Im, Jungho; Song, Chang‐Keun

doi:10.1016/j.atmosenv.2023.119951

Cited by 5 publications

(2 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to LUT-based AOD calculations that require iteration or interpolation processes [17], the retrieval of the AOD using a trained machine learning model is instantaneous [22]. Benefiting from this advantage, many classical machine learning models have been applied to describe the nonlinear relationships between satellite measurements and the AOD, such as the fully connected neural network (FCNN), gradient boosting framework (LGBM) [23,24], support vector machine (SVM) [21], and backpropagation neural network (BPNN) [17]. These methods have the advantage of satellite aerosol retrieval but are affected by the training sample.…”

Section: Introductionmentioning

confidence: 99%

Wide and Deep Learning Model for Satellite-Based Real-Time Aerosol Retrievals in China

Luo,

Zou,

Zang

et al. 2024

Atmosphere

View full text Add to dashboard Cite

Machine learning methods have been recognized as rapid methods for satellite-based aerosol retrievals but have not been widely applied in geostationary satellites. In this study, we developed a wide and deep learning model to retrieve the aerosol optical depth (AOD) using Himawari-8. Compared to traditional deep learning methods, we embedded a “wide” modeling component and tested the proposed model across China using independent training (2016–2018) and test (2019) datasets. The results showed that the “wide” model improves the accuracy and enhances model interpretability. The estimates exhibited better accuracy (R2 = 0.81, root-mean-square errors (RMSEs) = 0.19, and within the estimated error (EE) = 63%) than those of the deep-only models (R2 = 0.78, RMSE = 0.21, within the EE = 58%). In comparison with extreme gradient boosting (XGBoost) and Himawari-8 V2.1 AOD products, there were also significant improvements. In addition to higher accuracy, the interpretability of the proposed model was superior to that of the deep-only model. Compared with other seasons, higher contributions of spring to the AOD concentrations were interpreted. Based on the application of the wide and deep learning model, the near-real-time variation of the AOD over China could be captured with an ultrafine temporal resolution.

show abstract

Section: Introductionmentioning

confidence: 99%

Wide and Deep Learning Model for Satellite-Based Real-Time Aerosol Retrievals in China

Luo,

Zou,

Zang

et al. 2024

Atmosphere

View full text Add to dashboard Cite

show abstract

“…Spaceborne observations, providing near-global coverage, have effectively overcome the spatial constraints of ground-based stations [24][25][26][27][28][29][30]. Passive sensors, such as the MODerate resolution Imaging Spectroradiometer (MODIS), onboard Terra, and Aqua satellites, have supplied the scientific community with multi-year records of the columnar aerosol optical depth (AOD) since 2000 [31][32][33][34][35]. Advanced aerosol observations have been enabled by sensors such as the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) onboard the CALIPSO (Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation) satellite, deploying active remote sensing techniques [36].…”

Section: Introductionmentioning

confidence: 99%

Assessing Lidar Ratio Impact on CALIPSO Retrievals Utilized for the Estimation of Aerosol SW Radiative Effects across North Africa, the Middle East, and Europe

Moustaka,

Korras-Carraca,

Papachristopoulou

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

North Africa, the Middle East, and Europe (NAMEE domain) host a variety of suspended particles characterized by different optical and microphysical properties. In the current study, we investigate the importance of the lidar ratio (LR) on Cloud-Aerosol Lidar with Orthogonal Polarization–Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIOP-CALIPSO) aerosol retrievals towards assessing aerosols’ impact on the Earth-atmosphere radiation budget. A holistic approach has been adopted involving collocated Aerosol Robotic Network (AERONET) observations, Radiative Transfer Model (RTM) simulations, as well as reference radiation measurements acquired using spaceborne (Clouds and the Earth’s Radiant Energy System-CERES) and ground-based (Baseline Surface Radiation Network-BSRN) instruments. We are assessing the clear-sky shortwave (SW) direct radiative effects (DREs) on 550 atmospheric scenes, identified within the 2007–2020 period, in which the primary tropospheric aerosol species (dust, marine, polluted continental/smoke, elevated smoke, and clean continental) are probed using CALIPSO. RTM runs have been performed relying on CALIOP retrievals in which the default and the DeLiAn (Depolarization ratio, Lidar ratio, and Ångström exponent)-based aerosol-speciated LRs are considered. The simulated fields from both configurations are compared against those produced when AERONET AODs are applied. Overall, the DeLiAn LRs leads to better results mainly when mineral particles are either solely recorded or coexist with other aerosol species (e.g., sea-salt). In quantitative terms, the errors in DREs are reduced by ~26–27% at the surface (from 5.3 to 3.9 W/m2) and within the atmosphere (from −3.3 to −2.4 W/m2). The improvements become more significant (reaching up to ~35%) for moderate-to-high aerosol loads (AOD ≥ 0.2).

show abstract

Satellite-informed smart sensor placement framework for near-optimal PM2.5 monitoring in urban areas

Chang-Silva,

Tariq,

Kim

et al. 2024

Environ Sci Pollut Res

View full text Add to dashboard Cite

Direct aerosol optical depth retrievals using MODIS reflectance data and machine learning over East Asia

Cited by 5 publications

References 77 publications

Wide and Deep Learning Model for Satellite-Based Real-Time Aerosol Retrievals in China

Wide and Deep Learning Model for Satellite-Based Real-Time Aerosol Retrievals in China

Assessing Lidar Ratio Impact on CALIPSO Retrievals Utilized for the Estimation of Aerosol SW Radiative Effects across North Africa, the Middle East, and Europe

Satellite-informed smart sensor placement framework for near-optimal PM2.5 monitoring in urban areas

Contact Info

Product

Resources

About