China has currently entered a critical stage of coordinated control of fine particulate matter(PM_(2.5))and ozone(O_(3)),it is thus of tremendous value to accurately acquire high-resolution PM_(2.5) and O_(3) data.In ...China has currently entered a critical stage of coordinated control of fine particulate matter(PM_(2.5))and ozone(O_(3)),it is thus of tremendous value to accurately acquire high-resolution PM_(2.5) and O_(3) data.In contrast to traditional studies that usually separately estimate PM_(2.5) and O_(3),this study proposes a knowledge-informed neural network model for their joint estimation,in which satellite observations,reanalysis data,and ground station measurements are used.The neural network architecture is designed with the shared and specific inputs,the PM_(2.5)-O_(3) interaction module,and the weighted loss function,which introduce the prior knowledge of PM_(2.5) and O_(3) into neural network modeling.Cross-validation(CV)results indicate that the inclusion of prior knowledge can improve the estimation accuracy,with R^(2) increasing from 0.872 to 0.911 and from 0.906 to 0.937 for PM_(2.5) and O_(3) estimation under samplebased CV,respectively.In addition,the proposed joint estimation model achieves comparable performance with the separate estimation model,but with higher efficiency.Mapping results of PM_(2.5) and O_(3) derived by the proposed model have demonstrated interesting findings in the spatial and temporal trends and variations over China.展开更多
基金supported in part by the National Natural Science Foundation of China(No.42201359)the Guangdong Basic and Applied Basic Research Foundation(No.2022A1515010492).
文摘China has currently entered a critical stage of coordinated control of fine particulate matter(PM_(2.5))and ozone(O_(3)),it is thus of tremendous value to accurately acquire high-resolution PM_(2.5) and O_(3) data.In contrast to traditional studies that usually separately estimate PM_(2.5) and O_(3),this study proposes a knowledge-informed neural network model for their joint estimation,in which satellite observations,reanalysis data,and ground station measurements are used.The neural network architecture is designed with the shared and specific inputs,the PM_(2.5)-O_(3) interaction module,and the weighted loss function,which introduce the prior knowledge of PM_(2.5) and O_(3) into neural network modeling.Cross-validation(CV)results indicate that the inclusion of prior knowledge can improve the estimation accuracy,with R^(2) increasing from 0.872 to 0.911 and from 0.906 to 0.937 for PM_(2.5) and O_(3) estimation under samplebased CV,respectively.In addition,the proposed joint estimation model achieves comparable performance with the separate estimation model,but with higher efficiency.Mapping results of PM_(2.5) and O_(3) derived by the proposed model have demonstrated interesting findings in the spatial and temporal trends and variations over China.
