Observation of the ocean is crucial to the studies of ocean dynamics, climate change, and biogeochemical cycle. However, current oceanic observations are patently insufficient, because the in situ observations are of difficulty and high cost while the satellite remote‐sensed measurements are mainly the sea surface data. To make up for the shortage of ocean interior data and make full use of the abundant satellite data, here we develop a data‐driven deep learning model to estimate ocean subsurface and interior variables from satellite‐observed sea surface data. Exclusively and simply using satellite data, three‐dimensional ocean temperature and salinity fields are successfully reconstructed, which are at 26 level depths from 0 to 2,000 m. We further design a scheme to increase the horizontal resolution from 1° to 1/4°, which is higher than the Argo gridded data. Estimations from our model are accurate, reliable, and stable for a wide range of research areas and periods. Dynamic height fields that are derived from the estimated temperature and salinity, as well as the associated ocean geostrophic flows, are also calculated and analyzed, which indicates the potentials of our model for reconstructing the ocean circulation fields as well. This study enriches oceanic observations with respect to vertical dimension and horizontal resolution, which can largely make up for the paucity of the subsurface and deep ocean observation, both before and during Argo era. This work also provides some new foundations for and insights into geoscience and climate change fields.

Floods are the among the most frequent and common natural disasters, causing numerous casualties and extensive property losses worldwide every year. Since flooding areas are often accompanied by cloudy and rainy weather, synthetic aperture radar (SAR) is one of the most powerful sensors for flood monitoring with capabilities of day-and-night and all-weather imaging. However, SAR images are prone to high speckle noise, shadows, and distortions, which affect the accuracy of water body segmentation. To address this issue, we propose a novel Modified DeepLabv3+ model based on the powerful extraction ability of convolutional neural networks for flood mapping from HISEA-1 SAR remote sensing images. Specifically, a lightweight encoder MobileNetv2 is used to improve floodwater detection efficiency, small jagged arrangement atrous convolutions are employed to capture features at small scales and improve pixel utilization, and more upsampling layers are utilized to refine the segmented boundaries of water bodies. The Modified DeepLabv3+ model is then used to analyze two severe flooding events in China and the United States. Results show that Modified DeepLabv3+ outperforms competing semantic segmentation models (SegNet, U-Net, and DeepLabv3+) with respect to the accuracy and efficiency of floodwater extraction. The modified model training resulted in average accuracy, F1, and mIoU scores of 95.74%, 89.31%, and 87.79%, respectively. Further analysis also revealed that Modified DeepLabv3+ is able to accurately distinguish water feature shape and boundary, despite complicated background conditions, while also retaining the highest efficiency by covering 1140 km² in 5 min. These results demonstrate that this model is a valuable tool for flood monitoring and emergency management.

Accurately retrieving ocean interior parameters from remote sensing observations is essential for ocean and climate studies because direct observations are sparse and costly. Furthermore, high-resolution structure of seawater properties is critical for understanding the oceanic processes and changes on multiple scales. Here, we designed a new method based on a deep neural network to retrieve subsurface temperature anomaly (STA) and subsurface salinity anomaly (SSA) in the Pacific Ocean at high (1/4°) and super (1/12°) horizontal resolution. We utilized multisource satellite-observed sea surface data (e.g., sea level, temperature, salinity, and wind vector) as inputs. The results revealed that our model retrieved the high- and super-resolution STA/SSA with high accuracy, and the model was reliable in a wide range of depths (near surface to 4000 m) and times (all months in 2014). Regarding the high-resolution STA (SSA) estimation, the average coefficient of determination ( $R^{2}$ ) was 0.984 (0.966), and the average root-mean-squared error (RMSE) was 0.068 °C (0.016 psu). For the super-resolution STA, the average $R^{2}$ was 0.988 and RMSE was 0.093 °C. Here, we established an effective technique that improved the resolution and accuracy of estimating the ocean interior parameters from satellite observation. The new technique provides some new insights into oceanic observation and dynamics.

On 22 December 2020, HISEA-1, the first C-band SAR small satellite for ocean remote sensing, was launched from the coastal Wenchang launch site. Though small in weight, the images it produced have a high spatial resolution of 1 m and a large observation width of 100 km. The first batch of images obtained within the first week after the launch confirmed the rich information in the data, including sea ice, wind, wave, rip currents, vortexes, ships, and oil film on the sea, as well as landmark buildings. Furthermore, geometric characteristics of sea ice, wind vector, ocean wave parameter, 3D features of buildings, and some air-sea interface phenomena in dark spots could also be detected after relevant processing. All these indicate that HISEA-1 could be a reliable, remarkable, and powerful instrument for observing oceans and lands.