Atmospheric delay estimation method based on back propagation neural network

Abstract

The invention relates to the technical field of signal processing, in particular to an atmospheric delay estimation method, device and system based on a back propagation neural network and a storage medium, and the method comprises the steps: building the neural network through employing the related information of known atmospheric delay value pixel points of a to-be-observed region as training data and employing an error back propagation principle, training the neural network by using training data, inputting related information of unknown atmospheric delay value pixel points of the to-be-observed area into a trained network, and continuously solving new unknown atmospheric delay value pixel points on the basis of updating known information until atmospheric delay values of all pixel points are solved. The method can be applied to computer end software and is matched with corresponding hardware equipment. According to the method, the problem of low estimation precision caused by the fact that an atmospheric delay value model extracted in the prior art is not representative can be effectively solved, the influence of other errors of data on an estimation result in the prior art isovercome, and the atmospheric delay value estimation precision is improved.

Description

technical field [0001] The present invention relates to the technical field of signal processing, in particular to an atmospheric delay correction method, device, system and storage medium based on a backpropagation neural network in the technical field of radar signal processing. Background technique [0002] Differential Interferometry Synthetic Aperture Radar (DInSAR) is a microwave remote sensing technology with great potential. It can obtain centimeter-level or even millimeter-level surface deformation in deformation detection, and has been successfully applied, but its measurement accuracy is still limited by many. Constraints of factors: such as image registration error, complex terrain or decoherence noise in areas with more vegetation coverage, orbital error, phase unwrapping error in complex areas, atmospheric delay error, and terrain phase residuals that are not allowed to be introduced by external digital elevation models. Poor wait. Among these errors, due to t...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that in the process of atmospheric delay interpolation, only the corresponding relationship between atmospheric delay and elevation information is considered, while the corresponding relationship between atmospheric delay and spatial geographic location is ignored, which affects the accuracy of atmospheric delay correction

There are two shortcomings of this method. First, this method needs to obtain multiple SAR images in different time periods in the same area, generally more than 20, and atmospheric delay correction cannot be performed for data with a small amount of data.

Second, this method only relies on the information of the image itself to correct the atmospheric delay, and relies on the statistical characteristics of the atmospheric delay to estimate the atmospheric delay, ignoring the individual differences of atmospheric errors in different periods. In the statistical process, its accuracy is affected by data quality and other errors. Impact

Images