Retrieval of water vapor content in atmospheric column from Electro-L No. 3 spacecraft data using neural networks
V.D. Bloshchinskiy, A.A. Filei, E.I. Kholodov
Far-Eastern Center of State Research Center for Space Hydrometeorology В«Planeta», Khabarovsk, Russia
Keywords: MSU-GS, Electro-L, gas, water vapor, artificial neural network
Abstract
The application of a method based on artificial neural networks for assessing the total water vapor content in the atmospheric column from data of the MSU-GS satellite instrument of Electro-L No. 3 geostationary spacecraft is considered. The results of comparing the estimates of the total water vapor content from the MSU-GS data with MODIS satellite instrument data and AERONET measurements showed high agreement. The root mean square error when compared with the MODIS data was 0.311 cm, with the AERONET data, 0.409 cm, and the correlation was 98.2% and 84.7%, respectively. The results indicate the effectiveness of the method for determining the total content of water vapor for solving problems of atmospheric physics.
|