No abstract

Sea surface temperature (SST) forecasting is the task of predicting future values of a given sequence using historical SST data, which is beneficial for observing and studying hydroclimatic variability. Most previous studies ignore the spatial information in SST prediction and the forecasting models have limitations to process the large-scale SST data. A novel model of SST prediction integrated Deep Gated Recurrent Unit and Convolutional Neural Network (DGCnetwork) is proposed in this paper. The DGCnetwork has a compact structure and focuses on learning deep long-term dependencies in SST time series. Temporal information and spatial information are all included in our procedure. Differential Evolution algorithm is applied in order to configure DGCnetwork’s optimum architecture. Optimum Interpolation Sea Surface Temperature (OISST) data is selected to conduct experiments in this paper, which has good temporal homogeneity and feature resolution. The experiments demonstrate that the DGCnetwork significantly obtains excellent forecasting result, predicting SST by different lengths flexibly and accurately. On the East China Sea dataset and the Yellow Sea dataset, the accuracy of the prediction results is above 98% on the whole and all mean absolute error (MAE) values are lower than 0.33°C. Compared with the other models, root mean square error (RMSE), root mean square percentage error (RMSPE), and mean absolute percentage Error (MAPE) of the proposed approach reduce at least 0.1154, 0.2594, and 0.3938. The experiments of SST time series show that the DGCnetwork model maintains good prediction results, better performance, and stronger stability, which has reached the most advanced level internationally.

No abstract

Numerical experiments using hybrid coordinate ocean model (HYCOM) are designed to quantify the effects of wind wave-induced Coriolis-Stokes forcing (CSF) on mixed layer (ML) dynamics in a global context. CSF calculated by the wave parameters simulated by using the WaveWatch III (WW3) model is introduced as a new driving force for HYCOM. The results show that noticeable influence on ocean circulation in ML can be caused by CSF. Over most of the global oceans the direction of Stokes transport is different from that of the change in current transport caused by CSF. This is not unusual because CSF is normal to Stokes drift. However, the CSF-caused change in current transport and the wave-induced Stokes transport have the same magnitude. The seasonal variabilities of mixed layer temperature (MLT) and mixed layer depth (MLD) caused by CSF are analyzed, and the possible relationship between them is also given.

Diapycnal Mixing (DM) within the upper 2000m of the global ocean is calculated by a fine-scale parameterization using the multiyear-mean density gridded product that created by employing all the Argo float observations to date through the recently published equation of seawater TEOS-10. The geographic distribution of Argo-derived DM derived in this study is spatial-dependent and varies with latitude and depth. The magnitude and pattern of DM is favorably validated by comparisons with previous studies.Furthermore, the mixing coefficient tensor K is calculated and analyzed. Components of the tensor fitting for the geopotential coordinate models are also presented. It is found that the tensor components in horizontal direction, K xx and K yy , have similar magnitude and distribution pattern. In the vertical, K zz is enhanced over regions with rough topography and strong wind (e.g., Westerly region), suggesting agreement with previous estimates. This work presents a scheme to estimate the DM and mixing coefficient tensor using Argo observations, and offers a useful Argo-based mixing product for the purpose of promoting the study and modeling of ocean circulation and other processes.