Significant Wave Height Retrieval Based on Multivariable Regression Models Developed With CYGNSS Data

Authors:
Publisher website
Google Scholar
Abstract
This study utilizes L1B level data from reflected GNSS signals from the Cyclone GNSS (CYGNSS) mission to estimate sea surface Significant Wave Height (SWH). The Normalized Bistatic Radar Cross Section (NBRCS), Leading Edge Slope (LES), Signal to Noise Ratio (SNR) and Delay-Doppler Map Average (DDMA) are used as the key variables for the SWH retrieval. Eight other parameters including instrument gain and scatter area are also utilized as auxiliary variables to enhance the SWH retrieval performance. A variety of multi-variable regression models are investigated to clarify the relationship between the SWH and the variables by using the following five methods: Stepwise Linear Regression, Gaussian Support Vector Machine, Artificial Neural Network, Sparrow Search Algorithm–Extreme Learning Machine and Bagging Tree. Results show that among the five regression models developed, the Bagging Tree model performs the best with the Root Mean Square Error (RMSE) of 0.48 m and Correlation Coefficient (CC) of 0.82 when testing 1 million sets of data randomly selected, while the RMSE and CC of Bagging Tree model is 0.44 m and 0.73 in 4,500 National Data Buoy Center (NDBC) buoy testing dataset. Meanwhile, the Bagging Tree model also has the best generalization ability, which means it performs well in the practical application. In addition, the impacts of different input variables, the size of the training dataset and sea surface wind speed are also investigated. These findings are anticipated to serve as helpful guides for creating future SWH retrieval algorithms that are more advanced.
Funding Information
  • National Natural Science Foundation of China (Grants 42174022)

This publication has 42 references indexed in Scilit: