The consistent and long-term spaceborne Synthetic Aperture Radar (SAR) missions such as Sentinel-1 (S-1) provide high quality dual-polarized C-band images particularly suited to sea ice monitoring. SAR data is currently the primary source of information for sea ice charting made by human ice experts as a result of its integration with multiple information sources at different scales (mainly radiometers). The rise of deep learning now opens the prospect of automatic sea ice mapping. In this study, we investigate the potential of a Fully Convolutional Network (FCN) for the automatic estimation of Sea Ice Concentration (SIC).With input data down-sampled at 200 meters and an FCN architecture (depth and receptive field) duly parameterized, our approach is to mimic the work of an analyst who considers general context and does not necessarily use the highest possible resolution but speckle-noise polluted data. A comprehensive database is generated with 1320 dual-polarized S-1 scenes collocated with ice charts produced by MET Norway. A dedicated attention is paid to seasonal representativeness to ensure adequate performance for all sea ice types. Even if the FCN output is modeled as a categorical problem, the proposed architecture accounts for the semantic distances between SIC classes by introducing an auxiliary loss. A comparative benchmark with Ocean and Sea Ice Satellite Application Facility (OSISAF) and MET Norway SIC products is carried out, showing an Overall Accuracy of 78.2% for our 6-class classification approach. The FCN model is shown to be evenly robust to sea ice seasonal variability and incidence angle.

Through the Synthetic Aperture Radar (SAR) embarked on the satellites Sentinel-1A and Sentinel-1B of the Copernicus program, a large quantity of observations is routinely acquired over the oceans. A wide range of features from both oceanic (e.g., biological slicks, icebergs, etc.) and meteorologic origin (e.g., rain cells, wind streaks, etc.) are distinguishable on these acquisitions. This paper studies the semantic segmentation of ten metoceanic processes either in the context of a large quantity of image-level groundtruths (i.e., weakly-supervised framework) or of scarce pixel-level groundtruths (i.e., fully-supervised framework). Our main result is that a fully-supervised model outperforms any tested weakly-supervised algorithm. Adding more segmentation examples in the training set would further increase the precision of the predictions. Trained on 20 × 20 km imagettes acquired from the WV acquisition mode of the Sentinel-1 mission, the model is shown to generalize, under some assumptions, to wide-swath SAR data, which further extents its application domain to coastal areas.

Remote sensing of rainfall events is critical for both operational and scientific needs, including for example weather forecasting, extreme flood mitigation, water cycle monitoring, etc. Ground-based weather radars, such as NOAA’s Next-Generation Radar (NEXRAD), provide reflectivity and precipitation estimates of rainfall events. However, their observation range is limited to a few hundred kilometers, prompting the exploration of other remote sensing methods, particularly over the open ocean, that represents large areas not covered by land-based radars. Here we propose a deep learning approach to deliver a three-class segmentation of SAR observations in terms of rainfall regimes. SAR satellites deliver very high resolution observations with a global coverage. This seems particularly appealing to inform fine-scale rain-related patterns, such as those associated with convective cells with characteristic scales of a few kilometers. We demonstrate that a convolutional neural network trained on a collocated Sentinel-1/NEXRAD dataset clearly outperforms state-of-the-art filtering schemes such as the Koch’s filters. Our results indicate high performance in segmenting precipitation regimes, delineated by thresholds at 24.7, 31.5, and 38.8 dBZ. Compared to current methods that rely on Koch’s filters to draw binary rainfall maps, these multi-threshold learning-based models can provide rainfall estimation. They may be of interest in improving high-resolution SAR-derived wind fields, which are degraded by rainfall, and provide an additional tool for the study of rain cells.

Synthetic Aperture Radar is known to be able to provide high-resolution estimates of surface wind speed. These estimates usually rely on a Geophysical Model Function (GMF) that has difficulties accounting for non-wind processes such as rain events. Convolutional neural network, on the other hand, have the capacity to use contextual information and have demonstrated their ability to delimit rainfall areas. By carefully building a large dataset of SAR observations from the Copernicus Sentinel-1 mission, collocated with both GMF and atmospheric model wind speeds as well as rainfall estimates, we were able to train a wind speed estimator with reduced errors under rain. Collocations with in-situ wind speed measurements from buoys show a root mean square error that is reduced by 27% (resp. 45%) under rainfall estimated at more than 1 mm/h (resp. 3 mm/h). These results demonstrate the capacity of deep learning models to correct rain-related errors in SAR products.

This paper introduces a data-driven approach to estimate precipitation rates from synthetic aperture radar (SAR) at a spatial resolution of 200 m per pixel. It addresses previous challenges related to the collocation of SAR and weather radar data, specifically the misalignment in collocations and the scarcity of rainfall examples under strong wind. To tackle these challenges, the paper proposes a multiobjective formulation, introducing patch-level components and an adversarial component. It exploits the full NEXRAD archive to look for potential collocations with Sentinel-1 data. With additional enhancements to the training procedure and the incorporation of additional inputs, the resulting model demonstrates improved accuracy in rainfall estimates and the ability to extend its performance to scenarios up to 15 m s⁻¹. Significance Statement: Identifying rainfall events in coastal areas is crucial for correcting meteorological models and preventing hazards. However, quantitatively measuring precipitation in open ocean and coastal areas is challenging due to the availability and range of ground-based weather radars. Satellite-based observations can provide rain information with extensive spatial coverage and high frequency but usually lack resolution. The present paper proposes to complement existing methods with synthetic aperture radar (SAR). In association with observations from weather radar, it outlines an architecture to derive a relationship between SAR information and the precipitation rate.

The satellites of the Copernicus program routinely acquire data over the ocean. In particular, the Sentinel-1 mission carries a Synthetic Aperture Radar. This instrument, when used over the ocean surface, is able to estimate the sea surface roughness, which is affected by several meteorological and oceanic processes such as wind speed, rainfall, convective activity, or changes in surface viscosity due to pollution or biological slicks. Sentinel-1A and Sentinel-1B were launched in 2014 and 2016, respectively, and although Sentinel-1B has been out of commission since December 2021, Sentinel-1C is planned for launch in 2023. Between 2014 and 2022, around 102k wide-swath observations (with a width of approximately 250 km) have been acquired over the Mediterranean Sea, with a resolution of 10 by 10 meters. In parallel, deep learning models dedicated to the segmentation of SAR observations have been developed. Open Sentinel-1 datasets have recently been published [1,2], which enable the acceleration of research by sharing this time-consuming dataset gathering task.We therefore present the Mediterranean Sentinel-1 dataset. It contains the observations as well as their inferences by deep learning models. The segmentation maps produced include the detection of convection cells, the delineation of biological slicks, the estimation of rainfall, and the estimation of wind speed, built to reduce rain-induced errors. We show that the detection of biological slicks from Sentinel-1 shows similarity with Sentinel-3 ocean color, highlighting the synergies between both sensors. The concentration of biological slicks can indicate gyres and is demonstrated to be affected by ship traffic. The estimation of rainfall obtained from a previous study [3] is compared with European weather radar, indicating good agreement.[1] Wang, C., Mouche, A., Tandeo, P., Stopa, J., Longépé, N., Erhard, G., Foster, R., Vandemark, D., & Chapron, B. (2018). Labeled SAR imagery dataset of ten geophysical phenomena from Sentinel-1 wave mode (TenGeoP-SARwv) [Data set]. SEANOE. https://doi.org/10.17882/56796[2] Huang, L., Liu, B., Li, B., Guo, W., Yu, W., Zhang, Z., & Yu, W. (2018). OpenSARShip: A Dataset Dedicated to Sentinel-1 Ship Interpretation. In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (Vol. 11, Issue 1, pp. 195–208). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/jstars.2017.2755672[3] Colin, A., Tandeo, P., Peureux, C., Husson, R., Longepe, N., & Fablet, R. (2022). Rain Rate Estimation with SAR using NEXRAD measurements with Convolutional Neural Networks (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2207.07333