期刊文献+
共找到1篇文章
< 1 >
每页显示 20 50 100
Joint estimation of PM_(2.5) and O_(3) over China using a knowledge-informed neural network 被引量:2
1
作者 tongwen li Qianqian Yang +1 位作者 Yuan Wang Jingan Wu 《Geoscience Frontiers》 SCIE CAS CSCD 2023年第2期282-294,共13页
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
关键词 PM_(2.5) O_(3) Joint estimation Knowledge-informed neural network
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部