The sea surface temperature (SST) is an important parameter of the energy balance on the Earth’s surface. SST prediction is crucial to marine production, marine protection, and climate prediction. However, the current SST prediction model still has low precision and poor stability. In this study, a medium and long-term SST prediction model is designed on the basis of the gated recurrent unit (GRU) neural network algorithm. This model captures the SST time regularity by using the GRU layer and outputs the predicted results through the fully connected layer. The Bohai Sea, which is characterized by a large annual temperature difference, is selected as the study area, and the SSTs on different time scales (monthly and quarterly) are used to verify the practicability and stability of the model. The results show that the designed SST prediction model can efficiently fit the results of the real sea surface temperature, and the correlation coefficient is above 0.98. Regardless of whether monthly or quarterly data are used, the proposed network model performs better than long short-term memory in terms of stability and accuracy when the length of the prediction increases. The root mean square error and mean absolute error of the predicted SST are mostly within 0–2.5 °C.

Atmospheric circulation associated with the Arctic dipole (AD) pattern plays a crucial role in modulating the variations of summertime sea ice concentration (SIC) within the Pacific Arctic sector (PAS). Based on reanalysis data and satellite observations, we found that the impacts of atmospheric circulation associated with a positive AD (AD+) on SIC change over different regions of the PAS [including the East Siberian Sea (ESS), Beaufort and Chukchi Seas (BCS), and Canadian Arctic Archipelago (CAA)] are dependent on the phase shifts of Pacific decadal oscillation (PDO). Satellite observations reveal that SIC anomalies, influenced by AD+ during PDO− relative to that during PDO+, varies significantly in summer by 4.9%, −7.3%, and −6.4% over ESS, BCS, and CAA, respectively. Overall, the atmospheric anomalies over CAA and BCS in terms of specific humidity, air temperature, and thereby downward longwave radiation (DLR), are enhanced (weakened) in the atmospheric conditions associated with AD+ during PDO− (PDO+). In these two regions, the larger (smaller) increases in specific humidity and air temperature, associated with AD+ during PDO− (PDO+), are connected to the increased (decreased) poleward moisture flux, strengthened (weakened) convergence of moisture and heat flux, and in part to adiabatic heating. As a consequence, the DLR and surface net energy flux anomalies over the two regions are reinforced in the atmospheric scenarios associated with AD+ during PDO− compared with that during PDO+. Therefore, smaller SIC anomalies are identified over CAA and BCS in the cases related to AD+ during PDO− than during PDO+. Essentially, the changes of the DLR anomaly in CAA and BCS are in alignment with geopotential height anomalies, which are modulated by the anticyclonic circulation pattern in association with AD+ during varying PDO phases. In contrast, the SIC changes over ESS is primarily attributed to the variations in mechanical wind forcing and sea surface temperature (SST) anomalies. The cloud fraction anomalies associated with AD+ during different PDO phases are found not to be a significant contributor to the variations of sea ice anomaly in the studied regions. Given the oscillatory nature of PDO, we speculate that the recent shift to the PDO+ phase may temporarily slow the observed significant decline trend of the summertime SIC within PAS of the Arctic.

Based on the optimal interpolation (OI) algorithm, a daily fusion product of high-resolution global ocean columnar atmospheric water vapor with a resolution of 0.25° was generated in this study from multisource remote sensing observations. The product covers the period from 2003 to 2018, and the data represent a fusion of microwave radiometer observations, including those from the Special Sensor Microwave Imager Sounder (SSMIS), WindSat, Advanced Microwave Scanning Radiometer for Earth Observing System sensor (AMSR-E), Advanced Microwave Scanning Radiometer 2 (AMSR2), and HY-2A microwave radiometer (MR). The accuracy of this water vapor fusion product was validated using radiosonde water vapor observations. The comparative results show that the overall mean deviation (Bias) is smaller than 0.6 mm; the root mean square error (RMSE) and standard deviation (SD) are better than 3 mm, and the mean absolute deviation (MAD) and correlation coefficient (R) are better than 2 mm and 0.98, respectively.

The use of remote sensing data, whether for change detection, spatial and temporal analysis, or numerical simulation of water bodies, requires a complete data set. Here, high temporal and spatial resolution sea surface temperature (SST) data for the Arctic are produced based on optimal interpolation and data reconstruction algorithms with a temporal resolution of 12 h and a spatial resolution of 9 km. The accuracy of the reconstructed data sets is verified using Argo measurements to demonstrate the validity and reliability of the data interpolation empirical orthogonal functions method. The root mean square error of the fusion data (a temporal resolution of 12 h) is relatively stable, ranging from 0.49°C to 0.62°C. In comparison with remote sensing systems (RSS) MW-IR SST and Advanced Very High Resolution Radiometer (AVHRR) OISST, the accuracy of the fusion data (a temporal resolution of 24 h) is in the range of 0.48–0.65°C, while that of the MW-IR SST is in the range of 0.48–0.60°C and AVHRR OISST is in the range of 0.66–0.79°C. The fusion data is more accurate than those of AVHRR OISST, and there is no obvious difference with RSS MW-IR SST.

The present study utilizes the backward propagation neural network (BPNN) and the dual-branch convolutional neural network (DB-CNN) algorithms to construct models for estimating significant wave height (SWH) from polarimetric Gaofen-3 SAR wave mode data, using a dataset of 11 164 images that are collocated with SWH from the European Centre for Medium-Range Weather Forecasts fifth generation reanalysis (ERA5). The models are assessed and compared across nine polarizations [vertical–vertical (VV), horizontal–horizontal (HH), RL, vertical–horizontal (VH), horizontal-vertical (HV), RR, 45° linear, RV, and RH] and various sea states using the SAR-ERA5 test samples as well as buoy and altimeter SWH observations. The results demonstrate the robust performance of BPNN models, with RMSEs around 0.30–0.32 m on SAR-ERA5 test data, 0.32–0.48 m on buoy data, 0.40–0.48 m on Jason-3 data, and 0.36–0.42 m on SARAL data. By comparison, the DB-CNN models, which additionally include two-dimensional (2-D) image spectra as input, only exhibit improved performance at VV, 45° linear, and RL polarizations, while showing negligible improvement at HH, RV, and RH polarizations and a notable degradation at VH, HV, and RR polarizations. Furthermore, the DB-CNN models generally fail to improve the overestimation (underestimation) in low (high) seas, and they even aggravate the overestimation (underestimation) under most polarizations. Additionally considering the heightened complexity, increased vulnerability to overfitting, and training times that are more than 200 times longer, the use of complex deep learning network structures to incorporate 2-D spectral information appears to be operationally limited for SAR SWH retrieval.