Knowledge based convolutional transformer for joint estimation of PM2.5 and O3 concentrations

• Published in: Scientific reports Vol. 15; no. 1; pp. 25340 - 16
• Main Authors: Ren, Ying, Wang, Siyuan, Xia, Bisheng, Xia, Biesheng
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 14.07.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705; 704/106/35; Aerosols; Air pollution; Convtrans; Deep learning; Design; Environmental monitoring; Humanities and Social Sciences; Humidity; Joint Estimation; Knowledge; Machine learning; multidisciplinary; Neural networks; Particulate matter; PM2.5; Pollutants; Radiation; Remote sensing; Science; Science (multidisciplinary); Spatial variations; Time series; VOCs; Volatile organic compounds; Beijing China; China; Convtrans; Joint Estimation; PM; Knowledge; O
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-95019-5

Most of the methods for predicting air pollutant concentrations are targeting at single pollutants, which is time-consuming and laborious. To solve this problem, this study proposes a Convolutional Transformer (Convtrans) model that incorporates knowledge to make a collaborative estimation of PM 2.5 and O 3 by combining ground, satellite, and reanalysis data. Knowledge is introduced into the model by the shared and specific inputs, the PM 2.5 -O 3 interaction module, and the weighted loss function designed with the correlation between PM 2.5 and O 3 concentrations. To verify the accuracy of the Convtrans model, its prediction result was compared with that of CNN-LSTM, Transformer, RF, and XGB models. Estimating the pollutant concentration in typical Chinese cities, the cross-validation results show that Convtrans has the minimum error (PM 2.5 :RMSE = 6.136 µg/m³, O 3 :RMSE = 8.250 µg/m³) and the highest prediction accuracy (PM 2.5 :R 2  = 0.923, O 3 :R 2  = 0.898). Finally, a map of pollutant concentrations was drawn according to the pollutant concentration values predicted by the model, showing the spatial variations of pollutant. This study indicates that it is feasible to integrate knowledge into a data-driven model for a joint estimation of atmospheric pollutant concentrations. In addition, the joint estimation framework for pollutants proposed in this study can be applied to multivariate retrieval or estimation in multiple fields.