Improved retrievals of aerosol optical depth and fine mode fraction from GOCI geostationary satellite data using machine learning over East Asia

Kang, Yoojin; Kim, Miae; Kang, Eunjin; Cho, Dongjin; Im, Jungho

doi:10.1016/j.isprsjprs.2021.11.016

Cited by 52 publications

(9 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research indicates that CMI observations, particularly the blue band, contain valuable information regarding AOD levels. In 2022, Yoojin in [56] utilized GOCI geostationary satellite data to improve retrievals of AOD using a light GBR (LGBM) model. They achieved R² of 0.92 by showing CH01 (blue band at 0.412 µm) as the most informative feature.…”

Section: B Shap Analysismentioning

confidence: 99%

High-Frequency Mapping of Downward Shortwave Radiation from GOES-R Using Gradient Boosting

Ranjbar,

Losos,

Hoffman

et al. 2024

Preprint

View full text Add to dashboard Cite

This study investigates high-frequency mapping of downward shortwave radiation (DSR) at Earth's surface using the Advanced Baseline Imager (ABI) instrument mounted on Geostationary Operational Environmental Satellite -R Series (GOES-R). The existing GOES-R DSR product (DSR ABI ) offers hourly temporal resolution and spatial resolution of 0.25 o . To enhance these resolutions, we explore machine learning (ML) for DSR estimation at the native temporal resolution of GOES-R Level-2 Cloud and Moisture Imagery (CMI) product (five minutes) and its native spatial resolution of two-kilometer at nadir. We compared four common ML regression models through the Leave-One-Out Cross-Validation (LOOCV) algorithm for robust model assessment against ground measurements from AmeriFlux and SURFRAD networks. Results show that Gradient Boosting Regression (GBR) achieves the best performance (R² = 0.916, RMSE = 88.05 W m -2 ) with efficient computation compared to Long Short-Term Memory (LSTM), which exhibited similar performance. DSR estimates from the GBR model (DSR ALIVE ) outperform DSR ABI across various temporal resolutions and sky conditions. DSR ALIVE agreement with ground measurements at SURFRAD networks exhibits high accuracy at high temporal resolutions (five-minute intervals) with R² exceeding 0.85 and RMSE=122 W m -2 . We conclude that GBR offers a promising approach for high-frequency DSR mapping from GOES-R, enabling improved applications for near-real-time monitoring of terrestrial carbon and water fluxes.

show abstract

Section: B Shap Analysismentioning

confidence: 99%

High-Frequency Mapping of Downward Shortwave Radiation from GOES-R Using Gradient Boosting

Ranjbar,

Losos,

Hoffman

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Satellite-based AOT measurement and its prediction are essential in local and regional planning. [71] used multi-sensor satellite data, meteorological information, and groundbased parameters to predict AOT in the eastern part of China and Japan using machine learning classifiers. The R 2 value of their results (0.82 to 0.89) was similar to the values found in this study.…”

Section: Machine Learning For Predictive Analysismentioning

confidence: 99%

Seasonal Distribution of AOT and Its Relationship with Air Pollutants in Central Bangladesh Using Remote Sensing and Machine Learning Tools

Gomes¹,

Bhuiyan²,

Rahman³

2023

Preprint

View full text Add to dashboard Cite

Aerosol Optical Thickness (AOT) is one of the critical factors for global atmospheric conditions, climate change, and air pollution. AOT has been exposed as a major component of air pollution in Bangladesh. This paper aims to map the seasonal distribution of AOT from 2002-2022 and to explore the internal relationship between AOT and ten air pollutants using remote sensing and machine learning tools. These ten air pollutants are Particulate matter (PM2.5), Methane (CH4), Carbon monoxide (CO), Nitrogen dioxide (NO2), Formaldehyde (HCHO), Ozone (O3), Sulfur dioxide (SO2), Aerosol Particulate Radius (APR), Nitrogen oxide (NOx) and Black carbon (BC). The results show that the concentrations of AOT were higher in December-January-February (mean value 0.50) and March-April-May (mean value 0.50) seasons, mostly in the central, western, and southern parts of Dhaka, Narayanganj, and Munshiganj districts. AOT was a bit less in June-July-August (mean value 0.33) and September-October-November (mean value 0.37). This paper also revealed that the AOT was correlated positively with PM2.5 (0.60), CH4 (0.80), NO (0.76), and BC (0.83) while correlated negatively with CO (-0.66), HCHO (-0.16), SO2 (-0.41), APR (-0.48), and NOx (-0.20). From the machine learning, the Rational quadratic GPR (RME-0.0024, MAE-0.0015, R2-0.96), Matern 5/2 GPR (RMSE-0.0023, MAE-0.0015, R2-0.96), and Squared Exponential GPR (RMSE-0.0015, MAE-0.0015, R2-0.96) were found good classifiers to predict AOT. UN agencies, government line departments, and local and regional development councils for air pollution mitigation and long-term protective measures may use the paper's key results.

show abstract

“…The low accuracy of CNN AOD at JP4 is due to two reasons. First, high AOD more frequently occurs in China and South Korea than in Japan [52], and the annual average AOD in Japan is the lowest, so CNN tends to overestimate the AOD in Japan. Second, the data at JP4 are few (only 52 pairs of samples).…”

Section: Retrieval Performance Of the Cnn Model At Different Scalesmentioning

confidence: 99%

Aerosol Optical Depth Retrieval for Sentinel-2 Based on Convolutional Neural Network Method

Jiang,

Liu,

Jiao

2023

Atmosphere

View full text Add to dashboard Cite

Atmospheric aerosol significantly affects the climate environment and public health, and Aerosol Optical Depth (AOD) is a fundamental optical characteristic parameter of aerosols, so it is important to develop methods for obtaining AOD. In this work, a novel AOD retrieval algorithm based on a Convolutional Neural Network (CNN) method that could provide continuous and detailed aerosol distribution is proposed. The algorithm utilizes data from Sentinel-2 and Aerosol Robotic Network (AERONET) spanning from 2016 to 2022. The CNN AOD data are consistent with the AERONET measurements, with an R2 of 0.95 and RMSE of 0.049 on the test dataset. CNN demonstrates superior performance in retrieving AOD compared with other algorithms. CNN retrieves AOD well on high reflectance surfaces, such as urban and bare soil, with RMSEs of 0.051 and 0.042, respectively. CNN efficiently retrieves AOD in different seasons, but it performs better in summer and winter than in spring and autumn. In addition, to study the relationship between image size and model retrieval performance, image datasets of 32 × 32, 64 × 64 and 128 × 128 pixels were created to train and test the CNN model. The results show that the 128-size CNN performs better because large images contain rich aerosol information.

show abstract

Improved retrievals of aerosol optical depth and fine mode fraction from GOCI geostationary satellite data using machine learning over East Asia

Cited by 52 publications

References 58 publications

High-Frequency Mapping of Downward Shortwave Radiation from GOES-R Using Gradient Boosting

High-Frequency Mapping of Downward Shortwave Radiation from GOES-R Using Gradient Boosting

Seasonal Distribution of AOT and Its Relationship with Air Pollutants in Central Bangladesh Using Remote Sensing and Machine Learning Tools

Aerosol Optical Depth Retrieval for Sentinel-2 Based on Convolutional Neural Network Method

Contact Info

Product

Resources

About