Journal Article

First estimation of hourly full-coverage ground-level ozone from Fengyun-4A satellite using machine learning

Zhang, Han, Gao, Ling, Song, Yi, Tan, Wangshu, Yang, Fukun, Wu, Ronghua

2024

Overview

Ground-level ozone (O 3 ), renowned for its adverse impacts on human health and crop production, has garnered significant attention from governmental and public sectors. To address the limitations posed by sparse and uneven ground-level O 3 observations, this study proposes an innovative method for hourly full-coverage ground-level O 3 estimation using machine learning. Meteorological data from National Centers for Environmental Prediction global forecasting system, satellite data from Fengyun-4 A(FY-4 A) and Ozone Monitoring Instrument, emission inventory from Multi-resolution Emission Inventory for China, and other auxiliary data are utilized as input variables, while ground-based O 3 observations serve as the response variable. The method is applied on a monthly basis across China for the year 2022, resulting in the generation of an hourly full-coverage high-resolution (4 km) ground-level O 3 estimation, termed ML-derived-O 3 . Cross-validation results demonstrate the robustness of ML-derived-O 3 yielding a coefficient of determination ( R 2 ) of 0.96 (0.91) for sample-based (site-based) evaluations and a root-mean-square error (RMSE) of 9.22 (13.65) µ g m −3 . However, the date-based evaluation is less satisfactory due to the imbalanced training data, resulting from the pronounced daily variations in ground-level O 3 concentrations. Nevertheless, the seasonal and hourly ML-derived-O 3 exhibits high prediction accuracy, with R 2 values surpassing 0.95 and RMSE remaining below 7.5 µ g m −3 . This study marks a significant milestone as the first successful attempt to obtain hourly full-coverage ground-level O 3 data across China. The diurnal variation of ML-derived-O 3 demonstrates high consistency with ground-based observations, irrespective of clear or cloudy days, effectively capturing ground-level O 3 pollution exposure events. This novel estimation method will be employed to establish a long-term high spatial-temporal resolution ground-level O 3 dataset, which holds valuable applications for air pollution monitoring and environmental health research in future endeavors.

• Publisher: IOP Publishing
• Subject: Air monitoring / Air pollution / Crop production / Diurnal variations / Emission inventories / Environmental health / Environmental research / Fengyun-4A satellite / Ground-based observation / ground-level ozone / Learning algorithms / Machine learning / Meteorological data / Monitoring instruments / Ozone / Pollution monitoring / Root-mean-square errors / Temporal resolution