Significant Wave Height Retrieval Using XGBoost from Polarimetric Gaofen-3 SAR and Feature Importance Analysis

Empirical algorithms have become the mainstream of significant wave height (SWH) retrieval from synthetic aperture radar (SAR). But the plentiful features from multi-polarizations make the selection of input for the empirical model a problem. Therefore, the XGBoost models are developed and evaluated...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2023-01, Vol.15 (1), p.149
Main Authors: Song, Tianran, Yan, Qiushuang, Fan, Chenqing, Meng, Junmin, Wu, Yuqi, Zhang, Jie
Format: Article
Language:English
Subjects:
Algorithms
Calibration
Cut off wavelength
Empirical analysis
feature importance analysis
Gaofen-3 SAR wave mode
Kurtosis
Machine learning
Methods
Neural networks
Ocean waves
Polarimetry
Polarization
Radar
Radar cross sections
Remote sensing
Retrieval
Satellites
Skewness
SWH retrieval
Synthetic aperture radar
Wave height
Wavelength
XGBoost
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Empirical algorithms have become the mainstream of significant wave height (SWH) retrieval from synthetic aperture radar (SAR). But the plentiful features from multi-polarizations make the selection of input for the empirical model a problem. Therefore, the XGBoost models are developed and evaluated for SWH retrieval from polarimetric Gaofen-3 wave mode imagettes using the SAR features of different polarization combinations, and then the importance of each feature on the models is further discussed. The results show that the reliability of SWH retrieval models is independently confirmed based on the collocations of the SAR-buoy and SAR-altimeter. Moreover, the combined-polarization models achieve better performance than single-polarizations. In addition, the importance of different features to the different polarization models for SWH inversion is not the same. For example, the normalized radar cross section (NRCS), cutoff wavelength (λc), and incident angle (θ) have more decisive contributions to the models than other features, while peak wavelength (λp) and the peak direction (φ) have almost no contribution. Besides, NRCS of cross-polarization has a more substantial effect, and the λc of hybrid polarization has a stronger one than other polarization models.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15010149