Deriving gapless CO2 concentrations using a geographically weighted neural network: China, 2014–2020

Abstract

Listen

Translate article

• Long-term (2014–2020) and high-resolution gapless CO 2 data are generated for China. • Validation indicates high accuracy (R 2 = 0.936) of the novel reconstruction model. • Spatiotemporal trends of CO 2 are analyzed and interesting findings are revealed. In recent years, China has been experiencing increasing carbon dioxide (CO 2 ) concentration. Spaceborne satellites provide important support to monitor CO 2 , but the current instruments typically observe with narrow swaths and are frequently influenced by clouds and aerosols, resulting in extensive gaps in the satellite-derived CO 2 estimates. To this end, we aimed to reconstruct the CO 2 concentration products of the Orbiting Carbon Observatory-2 (OCO-2) to generate a monthly gapless CO 2 dataset (2014–2020) for China and investigate the spatio-temporal distribution of CO 2 concentration. The geographically weighted neural network (GWNN) model, which can consider temporal and spatial heterogeneity, was developed to establish the complicated relationships between OCO-2 CO 2 and the related variables, including CO 2 reanalysis data, meteorological variables, radiance data, and satellite normalized difference vegetation index (NDVI) data. Results showed a high correlation in R 2 and only a slight deviation in RMSE and MAPE in both simulated validation (R 2 , RMSE, and MAPE are 0.936, 1.360 ppm, and 0.242 %, respectively) and ground-based validation (R 2 , RMSE, and MAPE are 0.898, 1.685 ppm, and 0.317 %, respectively). Based on the gapless dataset, the CO 2 changes in China were investigated, and a periodically increasing trend with the growth rate of 2.517 ppm/yr was revealed. In addition, the anomaly analysis found that higher CO 2 concentrations exist in major cities, especially in highly developed regions. This study provides a gapless reconstruction approach for satellite-derived CO 2 and generates a long-term high-resolution CO 2 dataset for China, which will be valuable for China’s CO 2 emission reduction policy making.