Method for improving height measurement precision based on machine learning weighted average fusion feature extraction

Abstract

The invention discloses a method for improving height measurement precision based on machine learning weighted average fusion feature extraction, which utilizes a global navigation satellite system reflectometer to perform sea surface height measurement and can improve observation and inversion of a mesoscale process of an ocean by increasing space coverage of ocean surface observation. In order to make up the defects of a traditional inversion method, a novel machine learning weighted average fusion feature extraction method with airborne time delay waveform data as input and sea surface height as output is constructed on the basis of a machine learning fusion model in combination with a feature extraction principle. Meanwhile, two features of HALF and DER which are sensitive to sea surface height change are constructed based on a time delay waveform data set, and the influence of feature sets of different information details on sea surface height inversion precision is analyzed. The inversion precision of the sea surface height can be effectively improved by adopting a novel machine learning weighted average fusion feature extraction method, and the precision is improved by about 61%.

Description

technical field [0001] The invention belongs to the interdisciplinary technical fields of satellite altimetry and marine surveying and mapping, and in particular relates to a method for improving measurement accuracy based on machine learning weighted average fusion feature extraction. Background technique [0002] As an important ocean parameter, sea surface height plays an important role in establishing global tidal models, observing large-scale ocean circulation, and monitoring global sea level changes. The traditional spaceborne radar altimeter obtains the information of ocean physical parameters by continuously transmitting radar pulses to the earth and receiving sea surface echoes, which has the disadvantages of low coverage, long repetition period, and high satellite cost. GNSS-R technology is a new remote sensing technology for sea surface surveying in recent years. It retrieves the sea surface height by measuring the time delay between the reflected signal and the d...

AI Technical Summary

Problems solved by technology

[0005] However, machine learning models require a large number of labeled observations to train and build models

Spaceborne GNSS-R receivers can provide massive observation data, but the corresponding high-precision sea surface height is difficult to obtain

Images