Satellite-derived estimates of surface ozone by LESO: Extended application and performance evaluation

LESO: A ten-year ensemble of satellite-derived intercontinental hourly surface ozone concentrations

“…The details of this experiment are presented in Section “Technical Validation”. Besides, our previous work 14 , 15 and Figure S4 in “Supplementary Information” have demonstrated that the variability in O 3 total columns derived from different satellites is deemed to be statistically insignificant. The OMI data seems more advantageous due to the fact that TROPOMI, which was launched in October 2017, only offers Level-3 data products for dates subsequent to late 2018 19 , 34 , 35 .…”

“…The LESO ensemble was developed based on our previous short-term regional datasets 6 , 14 and has undergone substantial revision and enhancement, resulting in datasets that offer a greater level of spatial and temporal detail, spanning a period of more than a decade (not described elsewhere). An extensive validation of the LESO datasets has been conducted from three aspects.…”

“…The LEarning Surface Ozone (LESO) 6 , 14 is a subset of the Learning Air Pollutants from Satellite Observations (LAPSO) 15 system that employs advanced deep learning techniques to integrate multi-source datasets and infer spatial and temporal variability of air pollutants. The primary objective of LESO is to improve our understanding of the interactions between the atmospheric environment and human activities 6 .…”

“…We used the state-of-the-art deep forest method 16 , 17 to establish a relationship between the ground-based O 3 measurements and satellite observations, as well as meteorological reanalysis records. The deep forest method was suggested because it yielded more accurate estimation of O 3 concentrations, with an approximate increase of 30% in accuracy, as compared to conventional machine learning techniques such as shallow-layer neural networks and decision trees (e.g., multiple layer perceptron and random forest) 14 . The trained functions between the input variables (satellite observations and meteorological parameters) and output variables (surface O 3 measurements) were subsequently applied to produce gridded estimates of O 3 .…”

“…As most abundances are concentrated in the stratosphere, the signal of O 3 in the lower troposphere observed by nadir-viewing satellites is rather weak 18 , 19 . A comprehensive analysis using multiple satellite data sources has indicated that the application of deep learning techniques can achieve reliable and consistent estimation outcomes 14 . This capability enables the utilization of the vast potential of existing satellite data to derive surface ozone with high resolution and extensive coverage.…”