Monitoring optical properties of coastal and open ocean waters is crucial to assessing the health of marine ecosystems. Deep learning offers a promising approach to address these ecosystem dynamics, especially in scenarios where gap-free ground-truth data is lacking, which poses a challenge for designing effective training frameworks. Using an advanced neural variational data assimilation scheme (called 4DVarNet), we introduce a comprehensive training framework designed to effectively train directly on gappy data sets. Using the Mediterranean Sea as a case study, our experiments not only highlight the high performance of the chosen neural network in reconstructing gap-free images from gappy datasets but also demonstrate its superior performance over state-of-the-art algorithms such as DInEOF and end-to-end neural mapping schemes based CNN or UNet architectures.

This study presents an enhanced approach to ocean colour L4 product generation through the Adaptive Spatial and Multi-Variable Generalization of 4DVarNet - an innovative integration of deep neural networks with variational data assimilation proposed in [1]. We explore the model’s capabilities in generalizing across various geographical regions and bio-optical variables using datasets of the North Sea and the Mediterranean Sea. Our analysis and visualization show that 4DVarNet demonstrates a notable ability to adapt and scale, reducing significantly training cost thanks to this generalization ability.

Optical remote sensing is increasingly used to assess various sea surface biogeochemical parameters (e.g., Chl-a [1] , turbidity [2] ). If today's systems offer a better spatiotemporal coverage, it still depends on both the satellite revisit period and the cloud cover at the time of the acquisition. The resulting sea surface observations generally present large proportions of missing data, limiting their use. Typically, in our experiments, we worked with datasets containing up to 98% of missing data.

Characterization of suspended sediment dynamics in the coastal ocean provides essential information for scientific studies and operational challenges concerning, among others, turbidity, water transparency and the development of microorganisms using photosynthesis, which is critical for primary production. The complexity of the processes involved in sediment dynamics makes it difficult to predict surface dynamics. In the continuity of previous experiments, the 4DVarNet model having shown encouraging results with SSSC interpolations, it is tested in a 20-day forecasting problem. In addition to the learning architecture including the missing observation data, a protocol has been conceptualized to integrate different types of forcing to improve the reconstructions. The results of the method show that it is possible to produce satisfactory results. The results of the method show that it is possible to produce satisfactory results. The contribution of the input forcing is notable improving of 20% precision horizons. The study also highlights a characterization of the different input forcing and their effect on the system.

Due to complex natural and anthropogenic forcings, the dynamics of suspended sediments within the ocean water column remains difficult to monitor. Nowadays however, more and more available information is coming from in situ and satellite measurements, as well as from simulation models. Data assimilation methods propose to combine all this information to produce the most precise results, allowing better analyzes of the processes in play. Here a comparison of data-driven methods is presented. Optimal Interpolation (OI), Empirical Orthogonal Function (EOF) based and Kalman Filter based methods are compared to a new one using neural networks. The latter is a Data Interpolation method based on convolutional AutoEncoders (DinAE). Present results show that DinAE better performs compared to other methods, having the lowest error budget and the highest learning of high frequency events.

The capacity to monitor suspended sediment concentrations (SSCs) in the ocean, from surface to bottom, using data acquired by the future Meteosat Third-Generation (MTG)/flexible combined imager (FCI) satellite sensor has been quantified by observing system simulation experiments (OSSEs). The “true” ocean state for these experiments is based on a 15-month numerical simulation of hydrodynamic and sediment transport, configured to represent the highly dynamical waters of the English Channel under the influences of tides and waves. Simulated MTG/FCI hourly averaged acquisitions at a given location near the Isle of Wight have been processed via hidden Markov model combined with a statistical classification—based on self-organizing maps—of predicted vertical SSC profiles. The resulting experiments demonstrated that MTG/FCI images, despite their high temporal resolution, and because of many gaps due to nights and clouds over the English Channel, still require spatial interpolations to enhance the amount of information available at a given location. For an accurate determination of particle concentrations, time series of the main forcing (wind, tides, and waves) need to be included in the process: 1) as a crucial parameter correlated with the dynamics of large particles (sands) and 2) as an equally important parameter as satellite data themselves in the correlation with the dynamics of fine particles (silts).