Superior PM2.5 Estimation by Integrating Aerosol Fine Mode Data from the Himawari-8 Satellite in Deep and Classical Machine Learning Models

Abstract

Artificial intelligence is widely applied to estimate ground-level fine particulate matter (PM2.5) from satellite data by constructing the relationship between the aerosol optical thickness (AOT) and the surface PM2.5 concentration. However, aerosol size properties, such as the fine mode fraction (FMF), are rarely considered in satellite-based PM2.5 modeling, especially in machine learning models. This study investigated the linear and non-linear relationships between fine mode AOT (fAOT) and PM2.5 over five AERONET stations in China (Beijing, Baotou, Taihu, Xianghe, and Xuzhou) using AERONET fAOT and 5-year (2015–2019) ground-level PM2.5 data. Results showed that the fAOT separated by the FMF (fAOT = AOT × FMF) had significant linear and non-linear relationships with surface PM2.5. Then, the Himawari-8 V3.0 and V2.1 FMF and AOT (FMF&AOT-PM2.5) data were tested as input to a deep learning model and four classical machine learning models. The results showed that FMF&AOT-PM2.5 performed better than AOT (AOT-PM2.5) in modelling PM2.5 estimations. The FMF was then applied in satellite-based PM2.5 retrieval over China during 2020, and FMF&AOT-PM2.5 was found to have a better agreement with ground-level PM2.5 than AOT-PM2.5 on dust and haze days. The better linear correlation between PM2.5 and fAOT on both haze and dust days (dust days: R = 0.82; haze days: R = 0.56) compared to AOT (dust days: R = 0.72; haze days: R = 0.52) partly contributed to the superior accuracy of FMF&AOT-PM2.5. This study demonstrates the importance of including the FMF to improve PM2.5 estimations and emphasizes the need for a more accurate FMF product that enables superior PM2.5 retrieval.

Optimal Planning of Air Quality-Monitoring Sites for Better Depiction of PM2.5 Pollution across China

“…To fill these gaps, numerous studies ,− have proposed to integrate satellite aerosol optical depth (AOD) with ground-measured PM 2.5 using machine learning algorithms to obtain a better depiction of spatiotemporal variations of PM 2.5 . Due to existences of clouds and occurrences of snow/extreme haze, AOD-retrieving algorithms usually fail to offer valid values .…”

“…These issues could be addressed with advances in machine learning and growing volume of observations, and a wide range of algorithms or satellite retrievals (low-Earth orbit, geostationary, etc.) were explored previously. ,− Aerosol data assimilation methods were also developed to improve the spatiotemporal representation of PM 2.5 . , …”

Performance of MODIS Deep Blue Collection 6.1 Aerosol Optical Depth Products Over Indonesia: Spatiotemporal Variations and Aerosol Types

“…e Terra spacecraft crossed the equator at 10:30 am local standard time (LST), and the Aqua spacecraft crossed the equator at 13:30 LST [19]. Many studies have validated AOD between satellite-based and ground-based measurements in various parts of the world and found a high correlation [20][21][22][23].…”

Improved Bi-Angle Aerosol Optical Depth Retrieval Algorithm from AHI Data Based on Particle Swarm Optimization

“…Su et al (2020) proposed an algorithm combining DT and DB (Deep Blue) by building a monthly spectral base reflectance ratio library, which is a ratio library of 0.47 µm and 0.51 µm to 2.3 µm [25]. Many other studies have also greatly enriched AHI aerosol inversion [26][27][28][29].…”