Data-Driven Interpolation of Sea Surface Suspended Concentrations Derived from Ocean Colour Remote Sensing Data

Vient, Jean-Marie; Jourdin, Frédéric; Fablet, Ronan; Mengual, Baptiste; Lafosse, L.; Delacourt, Christophe

doi:10.3390/rs13173537

Cited by 5 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ever-increasing availability of observation data and numerical simulations also greatly contribute to the development and evaluation of learning-based and data-driven approaches as illustrated by the considered experimental setting based on an open data challenge 5 . We could apply and extend the proposed framework to other space-time geophysical products such as ocean colour [51,44], sea surface turbidity [50,42], sea and land surface temperature [5], sea surface currents [11,41]... Future challenges also involve joint calibration and interpolation issues for future satellite missions [22] as well as multimodal synergies between satellite data and other remote sensing and in situ data sources such as drifters [45,4], underwater acoustics data [8], moored buoys [23], argo profilers [13,17]... Especially, the latter might provide new ways to better monitor the interior of the ocean which cannot be directly observed from space.…”

Section: Discussionmentioning

confidence: 99%

Multimodal 4DVarNets for the reconstruction of sea surface dynamics from SST-SSH synergies

Fablet¹,

Febvre²,

Chapron³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The space-time reconstruction of ocean dynamics from satellite observations is a challenging inverse problem due to the associated irregular sampling of the sea surface. Satellite altimetry provides a direct observation of the sea surface height (SSH), which relates to the divergence-free component of sea surface currents. The associated sampling pattern prevents from retrieving fine-scale dynamics, typically below 10 days. By contrast, other satellite sensors provide higher-resolution observations of sea surface tracers such as sea surface temperature (SST). Multimodal inversion schemes then arise as appealing approaches. Though theoretical evidence supports the existence of an explicit relationship between sea surface temperature and sea surface dynamics under specific dynamical regimes, the generalization to the variety of upper ocean dynamical regimes is complex. Here, we investigate this issue from a physics-informed learning perspective. We introduce a trainable multimodal inversion scheme for the reconstruction of sea surface dynamics from multi-source satellite-derived observations, namely satellite-derived SSH and SST data. The proposed 4DVarNet schemes combine a variational formulation involving trainable observation and a priori terms with a trainable gradient-based solver. An observing system simulation experiment for a Gulf Stream region supports the relevance of our approach compared with state-of-the-art schemes. We report a relative improvement greater than 60% compared with the operational altimetry product in terms of root mean square error and resolved space-time scales. We discuss further the application and extension of the proposed approach for the reconstruction and forecasting of geophysical dynamics from irregularly-sampled satellite observations.

show abstract

Section: Discussionmentioning

confidence: 99%

Multimodal 4DVarNets for the reconstruction of sea surface dynamics from SST-SSH synergies

Fablet¹,

Febvre²,

Chapron³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Section 4 (Results), these concentrations will be called using the general term SSSC (surface suspended sediment concentration). For information, these SSSC values were already exploited by our team in order to obtain the present OSSE results in a previous article [19]. This latter article also provides condensed information on the validation of the MARS-MUSTANG simulations with the satellite data, which shows consistent behavior.…”

Section: Mars Model Simulations (For Osse)mentioning

confidence: 93%

“…This also includes neural network approaches dedicated to interpolation issues. Recent studies [17,19,32,34] have stressed the relevance of end-to-end deep learning architectures to address space-time interpolation issues with large missing data rates. Especially, 4DVarNet schemes, which rely on variational data assimilation formulation, have been shown to significantly outperform zero-filling learning-based strategies for interpolation problems [35].…”

Section: Dvarnet Schemementioning

confidence: 99%

“…These schemes are particularly relevant to addressing the irregular space-time sampling of satellite-derived sea surface dynamics. Following our previous study within an OSSE (Observing System Simulation Experiment) setting [19], we aim at evaluating whether such learning-based schemes apply to real satellite-derived datasets. Then, in this article, in the same way we designed real data experiments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

End-to-End Neural Interpolation of Satellite-Derived Sea Surface Suspended Sediment Concentrations

et al. 2022

Self Cite

View full text Add to dashboard Cite

The characterization of suspended sediment dynamics in the coastal ocean provides key information for both scientific studies and operational challenges regarding, among others, turbidity, water transparency and the development of micro-organisms using photosynthesis, which is critical to primary production. Due to the complex interplay between natural and anthropogenic forcings, the understanding and monitoring of the dynamics of suspended sediments remain highly challenging. Numerical models still lack the capabilities to account for the variability depicted by in situ and satellite-derived datasets. Through the ever increasing availability of both in situ and satellite-derived observation data, data-driven schemes have naturally become relevant approaches to complement model-driven ones. Our previous work has stressed this potential within an observing system simulation experiment. Here, we further explore their application to the interpolation of sea surface sediment concentration fields from real gappy satellite-derived observation datasets. We demonstrate that end-to-end deep learning schemes—namely 4DVarNet, which relies on variational data assimilation formulation—apply to the considered real dataset where the training phase cannot rely on gap-free references but only on the available gappy data. 4DVarNet significantly outperforms other data-driven schemes such as optimal interpolation and DINEOF with a relative gain greater than 20% in terms of RMSLE and improves the high spatial resolution of patterns in the reconstruction process. Interestingly, 4DVarNet also shows a better agreement between the interpolation performance assessed for an OSSE and for real data. This result emphasizes the relevance of OSSE settings for future development calibration phases before the applications to real datasets.

show abstract

“…Deep learning methods can effectively learn the hidden regularity in satellite data [36,37], thus being introduced for satellite data imputation. Jean-Marie et al [38] achieved the interpolation of SST data using a neural network, and proved that neural network is superior to the OI and EOF methods. Artificial Neural Network (ANN) has been also applied for the reconstruction of satellite data [30,33,39].…”

Section: Introductionmentioning

confidence: 99%

STA-GAN: A Spatio-Temporal Attention Generative Adversarial Network for Missing Value Imputation in Satellite Data

Wang

Hou

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Satellite data is of high importance for ocean environment monitoring and protection. However, due to the missing values in satellite data, caused by various force majeure factors such as cloud cover, bad weather and sensor failure, the quality of satellite data is reduced greatly, which hinders the applications of satellite data in practice. Therefore, a variety of methods have been proposed to conduct missing data imputation for satellite data to improve its quality. However, these methods cannot well learn the short-term temporal dependence and dynamic spatial dependence in satellite data, resulting in bad imputation performance when the data missing rate is large. To address this issue, we propose the Spatio-Temporal Attention Generative Adversarial Network (STA-GAN) for missing value imputation in satellite data. First, we develop the Spatio-Temporal Attention (STA) mechanism based on Graph Attention Network (GAT) to learn features for capturing both short-term temporal dependence and dynamic spatial dependence in satellite data. Then, the learned features from STA are fused to enrich the spatio-temporal information for training the generator and discriminator of STA-GAN. Finally, we use the generated imputation data by the trained generator of STA-GAN to fill the missing values in satellite data. Experimental results on real datasets show that STA-GAN largely outperforms the baseline data imputation methods, especially for filling satellite data with large missing rates.

show abstract

Data-Driven Interpolation of Sea Surface Suspended Concentrations Derived from Ocean Colour Remote Sensing Data

Cited by 5 publications

References 44 publications

Multimodal 4DVarNets for the reconstruction of sea surface dynamics from SST-SSH synergies

Multimodal 4DVarNets for the reconstruction of sea surface dynamics from SST-SSH synergies

End-to-End Neural Interpolation of Satellite-Derived Sea Surface Suspended Sediment Concentrations

STA-GAN: A Spatio-Temporal Attention Generative Adversarial Network for Missing Value Imputation in Satellite Data

Contact Info

Product

Resources

About