Validation and Calibration of Significant Wave Height and Wind Speed Retrievals from HY2B Altimeter Based on Deep Learning

Jiuke Wang,Lotfi Aouf,Yongjun Jia,Youguang Zhang

doi:10.3390/rs12172858

Abstract

HY2B is now the latest altimetry mission that provides global nadir significant wave height (SWH) and sea surface wind speed. The validation and calibration of HY2B are carried out against National Data Buoy Center (NDBC) buoy observations from April 2019 to April 2020. In general, the HY2B altimeter measurements agree well with buoy observation, with scatter index of 9.4% for SWH, and 15.1% for wind speed. However, we observed a significant bias of 0.14 m for SWH and −0.42 m/s for wind speed. A deep learning technique is novelly applied for the calibration of HY2B SWH and wind speed. Deep neural network (DNN) is built and trained to correct SWH and wind speed by using input from parameters provided by the altimeter such as sigma0, sigma0 standard deviation (STD). The results based on DNN show a significant reduction of the bias, root mean square error (RMSE), and scatter index (SI) for both SWH and wind speed. Several DNN schemes based on different combination of input parameters have been examined in order to obtain the best model for the calibration. The analysis reveals that sigma0 STD is a key parameter for the calibration of HY2B SWH and wind speed.

Highlights

Improving wave forecasting is a crucial issue for industrial activities at sea and for the protection of goods and people on the coast and at sea
From the assessment based on 1-year time-space matched data, HY2B significant wave height (SWH) gives a good accuracy with positive bias of 0.143 m and 9.4% scatter index (SI)
The bias of HY2B maintains positive around 0.15 m, while the SI keeps under 10% when SWH is greater than 1 m

Summary

Introduction

Improving wave forecasting is a crucial issue for industrial activities at sea and for the protection of goods and people on the coast and at sea. Buoys as in situ observations are the traditional ways of marine observation They are considered as the most accurate ways to obtain significant wave height and sea surface wind. After three decades of rapid development and improvement, the altimeter is becoming a widely used instrument to monitor the sea surface wave height and wind speed with high accuracy [1,2,3,4,5], and they have formed series, such as Jason [6,7,8] and HY2 series [9,10]. We will present how we use deep learning technique to improve the accuracy of the wave and wind observations by combining multiple measurements of parameters from altimeter HY2B.

Data and Validation of HY2B

Calibration of HY2B Wave SWH

Findings

Discussion and Conclusions