<p>Sea surface temperature (SST) is an important ocean variable affecting climate change. It plays an important role in the interactions between the ocean and the atmosphere, and it also has an effect on the transport of heat, freshwater, and carbon. Therefore, accurate SST prediction is necessary for understanding climate change and protecting ocean ecosystems. In this study, we proposed a hybrid model to predict SST in the tropical Pacific Ocean based on two single deep-learning models. Results indicate that the proposed hybrid model shows superior prediction accuracy at all lead times compared to the single model. Specifically, during El Niño periods, the root mean square error, mean absolute error, and Pearson correlation coefficient of the hybrid model forecasts were approximately 0.54 °C, 0.40 °C, and 0.98, respectively, while during La Niña periods, these metrics were 0.55 °C, 0.39 °C, and 0.98, respectively. Notably, the hybrid model was able to capture the spatial distribution of SSTs during the El Niño-Southern Oscillation (ENSO) events more accurately relative to a single model. Moreover, the prediction results of the hybrid model in different ocean regions exhibited lower prediction errors and higher correlations. The ablation experiments showed that sea surface wind (SSW) had different effects on SST at different times. By combining SST and SSW data, the model can make more-accurate predictions under different climatic conditions. The proposed hybrid model is able to predict SSTs quickly and accurately with better robustness during ENSO.</p>