Correcting Nonstationary Sea Surface Temperature Bias in NCEP CFSv2 Using Ensemble-Based Neural Networks

Sea surface temperature (SST) forecast products from the NCEP Climate Forecast System (CFSv2) that are widely used in climate research and prediction have nonstationary bias. In this study, we develop single-(ANN1) and three-hidden-layer (ANN3) neural networks and examine their ability to correct the SST bias in the NCEP CFSv2 extended seasonal forecast starting from July in the extratropical Northern Hemisphere. Our results show that the ensemble-based ANN1 and ANN3 can reduce the uncertainty associated with parameters assigned initially and dependence on random sampling. Overall, ANN1 reduces RMSE of the CFSv2 forecast SST substantially by 0.35 & DEG;C (0.34 & DEG;C) for the testing (training) data and ANN3 further reduces RMSE relatively by 0.49 & DEG;C (0.47 & DEG;C). Both the ensemble-based ANN1 and ANN3 can significantly reduce the spatially and temporally varying bias of the CFSv2 forecast SST in the Pacific and Atlantic Oceans, and ANN3 shows better agreement with the observation than that of ANN1 in some subregions. SIGNIFICANCE STATEMENT: Global coupled climate models are the primary tool for climate simulation and pre-diction and provide initial and boundary conditions to drive regional climate models. SST is an essential climate vari-able simulated and forecast by global climate models, which suffers substantial biases both spatially and temporally. We apply the ensemble averaging of both single-and three-hidden-layer neural networks on the NCEP CFSv2 SST forecast. They can correct the identified SST error, though ANN3 performs relatively better than that of ANN1. Thus, ensemble-based ANN3 isa useful SST bias correction approach.