Sea Level Fusion of Satellite Altimetry and Tide Gauge Data by Deep Learning in the Mediterranean Sea

Lianjun Yang,Xianwen Gao,Hailan Huang,Taoyong Jin,Taoyong Jin,Hailan Huang,Tilo Schöne,Mingyu Xiao,Hanjiang Wen

doi:10.3390/rs13050908

Abstract

Satellite altimetry and tide gauges are the two main techniques used to measure sea level. Due to the limitations of satellite altimetry, a high-quality unified sea level model from coast to open ocean has traditionally been difficult to achieve. This study proposes a fusion approach of altimetry and tide gauge data based on a deep belief network (DBN) method. Taking the Mediterranean Sea as the case study area, a progressive three-step experiment was designed to compare the fused sea level anomalies from the DBN method with those from the inverse distance weighted (IDW) method, the kriging (KRG) method and the curvature continuous splines in tension (CCS) method for different cases. The results show that the fusion precision varies with the methods and the input measurements. The precision of the DBN method is better than that of the other three methods in most schemes and is reduced by approximately 20% when the limited altimetry along-track data and in-situ tide gauge data are used. In addition, the distribution of satellite altimetry data and tide gauge data has a large effect on the other three methods but less impact on the DBN model. Furthermore, the sea level anomalies in the Mediterranean Sea with a spatial resolution of 0.25° × 0.25° generated by the DBN model contain more spatial distribution information than others, which means the DBN can be applied as a more feasible and robust way to fuse these two kinds of sea levels.

Highlights

Sea level rise, which is mainly caused by increasing ocean heat content and melting ice [1], has already become one of the most harmful climate change consequences
To evaluate the effect when no tide gauges were used as external control, only some of altimetry-derived gridded sea level anomaly (SLA) were selected as training data, and the remaining gridded SLAs were used as validation data
To evaluate the effect when tide gauges are included but the deviation between tide gauge and altimetry is ignored, the gridded SLAs within 20 km from the coast were used as virtual tide gauge SLAs, some of the altimetry-derived gridded SLAs further than 20 km from the coast and virtual tide gauge SLAs were selected as training data and the remaining virtual tide gauge SLAs were used as validation data

Summary

Introduction

Sea level rise, which is mainly caused by increasing ocean heat content and melting ice [1], has already become one of the most harmful climate change consequences. 46% of global assets will be at risk of flooding by 2100 as a result of the global sea level rise [2]. Monitoring and even predicting sea level change is becoming more and more necessary and important, especially in coastal areas. Tide gauges and satellite altimetry are two main technologies used to measure the sea level variation. The difficulties in building a reliable trend of sea level rise are mainly due to the sampling shortcomings of these two datasets [3]. The limitations of satellite altimetry have led to a lack of high-accuracy absolute sea level measurements in the near-shore areas

Methods

Results

Discussion

Conclusion