Bulletin of Surveying and Mapping ›› 2022, Vol. 0 ›› Issue (2): 90-94.doi: 10.13474/j.cnki.11-2246.2022.0049

Previous Articles     Next Articles

Study on inversion model of significant wave height from shore-based GNSS-IR by using NARX recurrent neural network

ZHANG Yi, ZHOU Li   

  1. School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, China
  • Received:2021-03-03 Published:2022-03-11

Abstract: Significant wave height is the main parameter of marine dynamic environment. This paper proposes a method to build the shore-based GNSS-IR significant wave height inversion model using NARX regression neural network. The method aims to explore how to use the data of a common single antenna measurement GNSS receiver to invert the significant wave height, and this paper gives the relevant processes and methods from data selecting, data processing to model construction. At the same time, this paper uses the two-year data from P231 station in the Stanford University Hopkins marine station for shore-based experiments. The results show that this method is suitable for the inversion application of significant wave height in the range of 0.1~2.5 m, and the min mean squared error of the inversion results of significant wave height is 0.01 m.

Key words: GNSS-IR, tide height, NARX, sea surface roughness, significant wave height

CLC Number: