Satellite remote sensing can detect and predict subsurface temperature and salinity structure within the ocean over large scales. In the era of big ocean data, making full use of multisource satellite observations to accurately detect and predict global subsurface thermohaline structure and advance our understanding of the ocean interior processes is extremely challenging. This study proposed a new deep learning-based method—bi-directional long short-term memory (Bi-LSTM) neural networks—for predicting global ocean subsurface temperature and salinity anomalies in combination with surface remote sensing observations (sea-surface temperature anomaly, sea-surface height anomaly, sea-surface salinity anomaly, and the northward and eastward components of sea-surface wind anomaly), longitude and latitude information (LON and LAT), and subsurface Argo gridded data. Because of the temporal dependency and periodicity of ocean dynamic parameters, the Bi-LSTM is good at time-series feature learning by considering the significant temporal feature of the ocean variability and can well improve the robustness and generalization ability of the prediction model. For December 2015 as an example, our average prediction results in an overall determination coefficient (R²) of 0.691/0.392 and a normalized root mean square error of 0.039 °C/0.051 PSU for subsurface temperature anomaly (STA)/subsurface salinity anomaly (SSA) prediction. This study sets up different cases based on different sea-surface feature combinations to predict the subsurface thermohaline structure and analyze the role of longitude and latitude information on Bi-LSTM prediction. The results show that in the prediction of STA, the contribution of LON + LAT to the model gradually increases with depth, whereas in the prediction of SSA, LON + LAT maintains a relatively significant contribution to the model at different depths. Meanwhile, in the STA and SSA prediction, the LAT plays a more significant role than LON. We also applied the model to bi-directional prediction for different months of 2010 and 2015 to prove the applicability and robustness of the model. This study suggests that Bi-LSTM is more advantageous in time-series modeling for predicting subsurface and deep ocean temperature and salinity structures, fully takes into account the timing dependence of global ocean data, and outperforms the classic random forest approach in predicting subsurface thermohaline structure from remote sensing data.

卫星遥感可以大规模检测和预测海洋中的地下温度和盐度结构。在大海洋数据时代，充分利用多源卫星观测数据来准确地检测和预测全球地下热盐结构并加深我们对海洋内部过程的理解是极具挑战性的。这项研究提出了一种基于深度学习的新方法-双向长期短期记忆（Bi-LSTM）神经网络-结合表面遥感观测（海面温度异常，海面高度异常，海面盐度异常以及海面风向的北向和东向分量），经度和纬度信息（LON和LAT），和地下Argo网格数据。由于海洋动力学参数的时间依赖性和周期性，Bi-LSTM通过考虑海洋变异性的显着时间特征，擅长时间序列特征学习，可以很好地提高预测模型的鲁棒性和泛化能力。以2015年12月为例，我们的平均预测得出的总体确定系数为R ²）（0.691 / 0.392）和归一化均方根误差（0.039°C / 0.051 PSU）用于预测地下温度异常（STA）/地下盐度异常（SSA）。这项研究基于不同的海面特征组合设置了不同的案例，以预测地下热盐的结构，并分析经度和纬度信息在Bi-LSTM预测中的作用。结果表明，在STA预测中，LON + LAT对模型的贡献随着深度的增加而逐渐增加，而在SSA预测中，LON + LAT在不同深度对模型的贡献相对较大。同时，在STA和SSA预测中，LAT的作用比LON更为重要。我们还将模型应用于2010年和2015年不同月份的双向预测，以证明该模型的适用性和鲁棒性。这项研究表明，Bi-LSTM在时间序列建模中更有利于预测地下和深海温度和盐度结构，充分考虑了全球海洋数据的时间依赖性，并且在预测地下热盐结构方面优于经典的随机森林方法来自遥感数据。