Reconstruction of the Basin‐Wide Sea‐Level Variability in the North Sea Using Coastal Data and Generative Adversarial Networks

Abstract

We present an application of generative adversarial networks (GANs) to reconstruct the sea level of the North Sea using a limited amount of data from tidal gauges (TGs). The application of this technique, which learns how to generate datasets with the same statistics as the training set, is explained in detail to ensure that interested scientists can implement it in similar or different oceanographic cases. Training is performed for all of 2016, and the model is validated on data from three months in 2017 and compared against reconstructions using the Kalman filter approach. Tests with datasets generated by an operational model ("true data") demonstrated that using data from only 19 locations where TGs permanently operate is sufficient to generate an adequate reconstruction of the sea surface height (SSH) in the entire North Sea. The machine learning (ML) approach appeared successful when learning from different sources, which enabled us to feed the network with real observations from TGs and produce high-quality reconstructions of the basin-wide SSH. Individual reconstruction experiments using different combinations of training and target data during the training and validation process demonstrated similarities with data assimilation when errors in the data and model were not handled appropriately. The proposed method demonstrated good skill when analyzing both the full signal and the low frequency variability only. It was demonstrated that GANs are also skillful at learning and replicating processes with multiple time scales. The different skills in different areas of the North Sea are explained by the different signal-tonoise ratios associated with differences in regional dynamics.

Detecting anomalous sea-level states in North Sea tide gauge data using of autoassociative Neural Network

“…Therefore, a question arises as to whether one can combine data from gauges and independent 2D maps of sea level (from models) to produce a consistent data set (covering all coastal locations at the same time and with high temporal resolution). A similar exercise was undertaken recently by Zhang et al (2020) for the North Sea and by Madsen et al (2019) for the Baltic Sea. Tide gauge stations operating along the North Sea coast provide high-quality records of sea level observations over a long period (Wahl et al, 2013).…”

“…Wenzel (2010) used Neural Networks for the reconstruction of monthly regional mean sea-level anomalies from 59 tide gauges worldwide. Zhang et al (2020) In contrast to all these applications, we will focus on the opposite: we will analyse data from an array of tide gauges in the North Sea simultaneously to identify situations in which their spatial correlations deviate greatly from the mean correlations.…”

Deep Learning for Geophysics: Current and Future Trends

“…Further works directly reconstruct SSH on a large and spatial and temporal space based on sparsely sampled data with CNN (Manucharyan et al, 2021). By using observation from satellite and coastal stations simultaneously, GAN can be used to reconstruct the SSH of the whole North-Sea (Zhang, Stanev, et al, 2020). DL also help estimate the iceberg in the pan-Antarctic near-coastal zone that covers the whole Antarctic continent for monitoring ice melt and sea level increasing (Barbat et al, 2019), and coastal inundation for a better understanding of the geospatial and temporal characteristics of coastal flooding (Liu et al, 2019 (Clausen & Nickisch, 2018).…”

“…Collecting data from different sources can help relieve the bottleneck of a limited number of training samples. Besides, using multimodal datasets can increase the quality and reliability of DL methods (Zhang, Stanev, et al, 2020). Feng, Fang et al (2020) used data integration to forecast streamflow where 23 variables were used, such as precipitation, solar radiation, and temperature.…”

“…For instance, on the STanford EArthquake Data set (STEAD), the earthquake detection accuracy is improved to 100% compared to 91% accuracy of the traditional STA/LTA (short time average over long time average) method (Mousavi, Zhu, Sheng, et al, 2019, Mousavi et al, 2020. DL makes characterizing the earth with high resolution on a large scale possible (Chattopadhyay et al, 2020;Chen et al, 2019;Zhang, Stanev, & Grayek, 2020). DL can even be used for discovering physical concepts (Iten et al, 2020), such as the solar system is heliocentric.…”