Articles | Volume 13, issue 3
Geosci. Model Dev., 13, 1499–1511, 2020
https://doi.org/10.5194/gmd-13-1499-2020
Geosci. Model Dev., 13, 1499–1511, 2020
https://doi.org/10.5194/gmd-13-1499-2020

Model evaluation paper 25 Mar 2020

Model evaluation paper | 25 Mar 2020

PM2.5 ∕ PM10 ratio prediction based on a long short-term memory neural network in Wuhan, China

Xueling Wu et al.

Viewed

Total article views: 1,225 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
702 497 26 1,225 28 26
  • HTML: 702
  • PDF: 497
  • XML: 26
  • Total: 1,225
  • BibTeX: 28
  • EndNote: 26
Views and downloads (calculated since 05 Aug 2019)
Cumulative views and downloads (calculated since 05 Aug 2019)

Viewed (geographical distribution)

Total article views: 1,007 (including HTML, PDF, and XML) Thereof 999 with geography defined and 8 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 22 Jan 2021
Download
Short summary
This paper presents a composite prediction system designed to improve the accuracy and applicability of PM2.5 / PM10 predictions. Based on remote sensing images, the aerosol optical thickness was obtained and corrected. Then, we selected PM2.5 / PM10-related factors from meteorological factors and air pollutants and compared the effects of several intelligent models in different prediction patterns. The results showed that the LSTM model had significant advantages in accuracy and stability.