A Multivariable Convolutional Neural Network for Forecasting Synoptic-Scale Sea Surface Temperature Anomalies in the South China Sea

The sea surface temperature anomaly (SSTA) plays a key role in climate change and extreme weather pro-cesses. Usually, SSTA forecast methods consist of numerical and conventional statistical models, and the former can be se-riously influenced by the uncertainty of physical parameterization schemes, the nonlinearity of ocean dynamic processes, and the nonrobustness of numerical discretization algorithms. Recently, deep learning has been explored to address fore-cast issues in the field of oceanography. However, existing deep learning models for ocean forecasting are mainly site spe-cific, which were designed for forecasting on a single point or for an independent variable. Moreover, few special deep learning networks have been developed to deal with SSTA field forecasts under typhoon conditions. In this study, a multi -variable convolutional neural network (MCNN) is proposed, which can be applied for synoptic-scale SSTA forecasting in the South China Sea. In addition to the SSTA itself, the surface wind speed and the surface current velocity are regarded as input variables for the prediction networks, effectively reflecting the influences of both local atmospheric dynamic forc-ing and nonlocal oceanic thermal advection. Experimental results demonstrate that MCNN exhibits better performance than a single-variable convolutional neural network (SCNN), especially for the SSTA forecast during the typhoon passage. While forecast results deteriorate rapidly in the SCNN during the passage of a typhoon, forecast errors in the MCNN can be effectively restrained to slowly increase over the forecast time due to the introduction of the surface wind speed in this network.