Oceanographic parameters, such as sea surface temperature, surface chlorophyll-a concentration, sea surface ice concentration, sea surface height, etc., are listed as Essential Climate Variables. Therefore, there is a crucial need for persistent and accurate measurements on a global scale. While in situ methods tend to be accurate and continuous, these qualities are difficult to scale spatially, leaving a significant portion of Earth’s oceans and seas unmonitored. To tackle this, various remote sensing techniques have been developed. One of the more prominent ways to measure the aforementioned parameters is via satellite spacecraft-mounted remote sensors. This way, spatial coverage is considerably increased while retaining significant accuracy and resolution. Unfortunately, due to the nature of electromagnetic signals, the atmosphere itself and its content (such as clouds, rain, etc.) frequently obstruct the signals, preventing the satellite-mounted sensors from measuring, resulting in gaps—missing data—in satellite recordings. One way to deal with these gaps is via various reconstruction methods developed through the past two decades. However, there seems to be a lack of review papers on reconstruction methods for satellite-derived oceanographic variables. To rectify the lack, this paper surveyed more than 130 articles dealing with the issue of data reconstruction. Articles were chosen according to two criteria: (a) the article has to feature satellite-derived oceanographic data (b) gaps in satellite data have to be reconstructed. As an additional result of the survey, a novel categorising system based on the type of input data and the usage of time series in reconstruction efforts is proposed.

In this paper, we discuss different approaches to optimal sensor placement and propose that an optimal sensor location can be selected using unsupervised learning methods such as self-organising maps, neural gas or the K-means algorithm. We show how each of the algorithms can be used for this purpose and that additional constraints such as distance from shore, which is presumed to be related to deployment and maintenance costs, can be considered. The study uses wind data over the Mediterranean Sea and uses the reconstruction error to evaluate sensor location selection. The reconstruction error shows that results deteriorate when additional constraints are added to the equation. However, it is also shown that a small fraction of the data is sufficient to reconstruct wind data over a larger geographic area with an error comparable to that of a meteorological model. The results are confirmed by several experiments and are consistent with the results of previous studies.

This work represents a modification of the Context Conditional Generative Adversarial Network as a novel implementation of a non-linear gap reconstruction approach of missing satellite-derived chlorophyll a concentration data. By adjusting the loss functions of the network to focus on the structural credibility of the reconstruction, high numerical and structural reconstruction accuracies have been achieved in comparison to the original network architecture. The network also draws information from proxy data, sea surface temperature, and bathymetry, in this case, to improve the reconstruction quality. The implementation of this novel concept has been tested on the Adriatic Sea. The most accurate model reports an average error of $0.06\mathrm{mg}{\mathrm{m}}^{-3}$ and a relative error of $3.87\%$. A non-deterministic method for the gap-free training dataset creation is also devised, further expanding the possibility of combining other various oceanographic data to possibly improve the reconstruction efforts. This method, the first of its kind, has satisfied the accuracy requirements set by scientific communities and standards, thus proving its validity in the initial stages of conceptual utilisation.

Extreme sea levels can lead to floods that cause significant damage to coastal infrastructure and put people's lives in danger. These floods are a result of physical processes occurring at various time and space scales, including sub-hourly scales. To estimate the contribution of sub-hourly sea level oscillations to extreme sea levels, raw sea level data from about 300 tide gauge stations along the European coasts, with a sampling resolution of less than 20 minutes, were collected. The data were obtained from: (1) the IOC-SLSMF website (290 stations); (2) National agencies (Portugal, Finland, Croatia –24 stations). Portions of the raw dataset had various data quality issues (i.e., spikes, shifts, drifts) hence quality control procedure was required. Out of range values, values with a 50 cm difference from one neighbouring value or a 30 cm difference from both neighbouring values, were automatically removed. The automatic spike detection procedure was carried out by removing values that differed by three standard deviations from a spline fitted with the least squares method. Following the automatic quality control, all remaining data were visually examined and spurious data were removed manually.The resulting data set contains sea level data from 2007. to 2021., with an average record length of approximately 7 years, however the length varies from a few months at some stations to 13 years at others. Tide gauges with longer records (>10 years) are based in the Baltic region, France and Spain, whereas the ones with shorter records (<3 years) are mostly based in the Eastern Mediterranean. The Western Mediterranean and western Europe have a high station coverage with records of various lengths. Tide gauges mostly provide data with a one-minute sampling frequency, however, some of them still record on a multi-minute scale (i.e., United Kingdom with 15 minutes and Norway and the Netherlands with 10 minutes sampling frequency).Preliminary statistical analyses were done, resulting with spatial and temporal distribution of contribution of high-frequency sea level oscillations to total sea level extremes along the European coasts.

Surface currents can be accurately measured remotely using high-frequency radars, with the drawback that those measurements are susceptible to external interference resulting in frequent gaps in data. In this article, we compare the gap-filling accuracy of four pattern recognition machine learning methods—k-means clustering, self-organizing maps, growing neural gas, and a generative adversarial network. Several dozen experiments are demonstrated using data from two different radars, exploring the possibilities of applications of feature engineering to reduce the dimensionality of the problem. Findings indicate how classical pattern recognition algorithms result in an average relative error of around 5%–10 $\%$ , while the generative adversarial network decreased that error, with significantly increased correlation.