Xinrong Wu

This study evaluates the accuracy of ERA5 10-m wind speed and significant wave height (SWH) using one-year hourly observations from 16 buoys in the Bohai and Yellow Seas. ERA5 agrees closely with the buoys (wind: Bias 0.04 m/s, root-mean-square error (RMSE) 1.40 m/s, scatter index (SI) 0.24, correlation coefficient (r) 0.90; SWH: Bias 0.11 m, RMSE 0.23 m, SI 0.30, r 0.94). Errors decrease offshore, and the control is offshore distance rather than water depth: a 2.5-fold depth change at fixed distance alters wind RMSE by 0.02 m/s, whereas a doubling of distance at fixed depth alters it by 0.22–0.24 m/s. Wind Bias has a marked diurnal cycle whose amplitude decreases offshore and reverses seasonally; SWH Bias stays positive but weakens in summer; both variables overestimate weak and underestimate strong conditions. The absolute errors of the two variables vary out of phase, so their correlation cancels (−0.40 to 0.02), whereas the relative errors remain strongly coupled (0.59–0.80). Above 13 m/s, ERA5 underestimates wind by 11% while overestimating SWH by 6%, an inconsistency that locates the high-sea-state error in the wave model rather than in the forcing. These quantified errors constrain design-wave estimation and Bias correction in coastal engineering.

The accumulated remote sensing data of altimeters and scatterometers have provided new opportunities for ocean state forecasting and have improved our knowledge of ocean–atmosphere exchanges. Studies on multivariate, multistep, spatiotemporal sequence forecasts of sea level anomalies (SLA) for different modalities, however, remain problematic. In this paper, we present a novel hybrid and multivariate deep neural network, named HMnet3, which can be used for SLA forecasting in the South China Sea (SCS). First, a spatiotemporal sequence forecasting network is trained by an improved convolutional long short-term memory (ConvLSTM) network using a channelwise attention mechanism and multivariate data from 1993 to 2015. Then a time series forecasting network is trained by an improved long short-term memory (LSTM) network, which is realized by ensemble empirical mode decomposition (EEMD). Finally, the two networks are combined by a successive correction method to produce SLA forecasts for lead times of up to 15 days, with a special focus on the open sea and coastal regions of the SCS. During the testing period of 2016–18, the performance of HMnet3 with sea surface temperature anomaly (SSTA), wind speed anomaly (SPDA), and SLA data is much better than those of state-of-the-art dynamic and statistical (ConvLSTM, persistence, and climatology) forecast models. Stricter testbeds for trial simulation experiments with real-time datasets are investigated, where the eddy classification metrics of HMnet3 are favorable for all properties, especially for those of small-scale eddies.