Satellite Remote Sensing Data and Lidar Data Fusion for Ozone Concentration Prediction

Strategic Insights -

Researchers from Shaanxi University of Technology have made a groundbreaking discovery in the field of supercomputing, successfully predicting atmospheric ozone concentration using a combination of satellite remote sensing data and Lidar data fusion. Their study, published in The Journal of Supercomputing, demonstrates the effectiveness of the RNN-CNN model in achieving accurate predictions of ozone concentration, with a root-mean-squared error of 18.13 and a mean absolute error of 11.64. The research has significant implications for intelligent prediction of atmospheric ozone concentration distribution.

Key Takeaways:

  • The study used a combination of satellite remote sensing data and Lidar data to predict atmospheric ozone concentration in western China.
  • The RNN-CNN model was constructed using the gated recurrent unit and convolutional neural network to achieve accurate predictions of ozone concentration.
  • The model achieved a root-mean-squared error of 18.13 and a mean absolute error of 11.64, indicating high accuracy.
  • The study showed that the ozone concentration in the north is higher and the ozone concentration in the south is lower in different seasons in western China.
  • The hourly change of ozone concentration reaches a trough around 9-10 o'clock and reaches a peak around 16-17 o'clock.
  • The research has reliable theoretical value and practical significance for intelligent prediction of atmospheric ozone concentration distribution.
  • Yuan Jiang, Guibao Wang, Ru Qiao, and Yongjie Zhu were involved in the research.

Statistics:

  • Root-mean-squared error: 18.13
  • Mean absolute error: 11.64
  • Index of agreement: 0.973
  • Ozone concentration in the north: higher
  • Ozone concentration in the south: lower
  • Hourly change of ozone concentration: reaches a trough around 9-10 o'clock and reaches a peak around 16-17 o'clock

Sources:

  • Data Fusion of Atmospheric Ozone Remote Sensing Lidar According To Deep Learning. The Journal of Supercomputing, 2021.
  • Yuan Jiang, Guibao Wang, Ru Qiao, and Yongjie Zhu. Shaanxi University of Technology.
  • The Journal of Supercomputing can be contacted at: Springer-Verlag, Van Godewijckstraat 30, 3311 Gz Dordrecht, Netherlands.
  • Yuan Jiang, Shaanxi University of Technology, School of Physics & Telecommunications Engineering, Hanzhong 723001, Shaanxi, People's Republic of China.
  • DOI: https://doi-org.sdpl.idm.oclc.org/10.1007/s11227-020-03537-y.