Prediction of Significant Wave Heights with Engineered Features from GNSS Reflectometry

Abstract

Estimating reflector heights at stationary GNSS sites with interferometric reflectometry (IR) is a well-established technique in ocean remote sensing. Additionally, IR offers the possibility to estimate the significant wave height (SWH) with a linear model using the damping coefficient from an inverse modelling applied to GNSS signal-to-noise ratio (SNR) observations. Such a linear model serves as a benchmark in the present study, where an alternative approach for the estimation of both SWH and reflector height is presented that is based on kernel regression and clustering techniques. In this alternative approach, the reflector height is estimated by analyzing local extrema occurring in the interference pattern that is present in GNSS SNR observations. Various predictors are derived from clustering statistics and the estimated reflector heights. These predictors are used for the SWH determination with supervised machine learning. Linear models, bagged regression trees, and artificial neural networks are applied and respective results are compared for various predictor sets. In a second step, damping coefficients obtained from the inverse modelling mentioned above are additionally taken into account as predictors. The usability of the alternative approach is demonstrated. Compared to the benchmark, a significant improvement in terms of accuracy is found for an artificial neural network with predictors from both the alternative and the inverse modelling approach.