Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm

Abstract

Due to the advantage of geostationary satellites, Himawari-8/AHI can provide near-real-time air quality monitoring over China with a high temporal resolution. Satellite-based aerosol optical depth (AOD) retrieval over land is a challenge because of the large surface contribution to the top of atmosphere (TOA) signal and the uncertainty of aerosol modes. Here, by combining satellite TOA reflectance, sun-sensor geometries, meteorological factors and vegetation information, we propose a data-driven AOD detection algorithm based on a deep neural network (DNN) model for Himawari-8/AHI. It is trained by sample data of 2018 and 2019 and is applied to derive hourly AODs over China in 2020. By comparison with ground-based AERONET measurements, R2 for DNN-estimated AOD is up to 0.8702, which is much higher than that for the AHI AOD product with R2 = 0.4869. The hourly AOD results indicate that the DNN model has a good potential in improving the performance of AOD retrieval in the early morning and in the late afternoon, and the spatial distribution is reliable for capturing the variation of aerosol pollution on the regional scale. By analyzing different DNN modeling strategies, it is found that seasonal modeling can hardly increase the accuracy of AOD retrieval to a certain extent, and R2 increases from 0.7394 to 0.8168 when meteorological features, especially air pressure, are involved in the model training.

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

“…The Himawari-8 aerosol product shows an overall higher AOD, which is not consistent with MODIS AOD and CNN AOD. The MODIS AOD product is more reliable than the Himawari-8 AOD product [34]. Specifically, the CNN AOD that is more similar to MODIS AOD can reasonably reflect the AOD concentration.…”

“…MODIS has provided scholars with different types of global aerosol products for decades, among which MODIS AOD standard products over land include AOD retrieved by the MAIAC algorithm, DT algorithm, DB algorithm, and combined Dark Target and Deep Blue (DTB) [34]. At present, the MODIS MAIAC aerosol products have been developed for the C6.0 version, and the DT, DB, and DTB aerosol products have been developed for the C6.1 version [28].…”

“…This mechanism can be used as a statistical method to extract remote sensing information for quantitative parameter retrieval problems. Chen et al [34] retrieved AOD in China based on Himawari-8 satellite data and deep neural networks, with a correlation coefficient of up to 0.87. Chen et al [35] developed an aerosol retrieval model based on Convolutional Neural Network (CNN), and 68% of the retrieved AOD values are within the MODIS expected error (EE) envelope over land of ± (0.05 + 15%).…”

Influence of industrial sustainability transition on air quality in a typical resource-exhausted city

“…Satellite remote sensing monitoring is now the most widely used technical method, especially for MODIS data because of their abundant information owning to their wide spectral range and large coverage area. In addition, some other satellite data such as NPP/VIIRS light data [ 15 , 16 ]、Landsat-8 image [ 17 ]、FY4A AGRI data [ 18 ] and Himawari-8 images [ 19 ] are also used for AOD remote sensing inversion.…”