Aerosol extinction coefficient inversion method base on feedback type RBF neural network

Abstract

The invention discloses an aerosol extinction coefficient inversion method base on a feedback type RBF neural network. The method includes the following steps: 1) training the RBF neural network by using input and expected output, wherein the power of historical echo signals is used as the input of the RBF neural network and aerosol extinction coefficients obtained from the historical echo signalsare used as the expected output of the RBF neural network; and 2) inverting the aerosol extinction coefficients based on the feedback type RBF neural network. The method uses the feedback type RBF neural network to invert the aerosol extinction coefficients and stores internal mechanisms between information in a network through the learning of sample patterns, which effectively avoids the uncertainty caused by a plurality of assumptions. The method has fast response speed and good robustness.

Description

technical field [0001] The invention relates to an aerosol extinction coefficient inversion method based on a feedback RBF neural network, belonging to the technical field of aerosol measurement. Background technique [0002] Atmospheric aerosol is a multiphase system composed of objects in different phases, suspended in the atmosphere, and composed of various solid or liquid particles, which will affect the development and changes of many physical and chemical processes in the atmospheric environment. The diameter of aerosol particles ranges from 0.001 to 100 μm, and they can stay in the atmosphere for at least several hours or even several days, thereby changing the composition and structure of the atmosphere, disrupting and destroying the original normal ecosystem. It is mainly distributed throughout the atmosphere and affects climate effects and thus human health. Therefore, it has very important practical significance to improve the atmospheric environment by detecting...

AI Technical Summary

Problems solved by technology

Then when inverting the extinction coefficient, since there are many variables in the radar equation, many variables are often replaced by empirical values ​​or assumptions for the convenience of calculation, such as the boundary value of the aerosol extinction coefficient, the aerosol extinction backscatter ratio, etc., so that the extinction There are many uncertain factors in the inversion of coefficients, which is obviously not conducive to the fine inversion of aerosol optical properties.

Images