Ziying Yang, Jiping Liu, Chaoyuan Yang, Yongyun Hu
{"title":"Correcting nonstationary sea surface temperature bias in NCEP CFSv2 using Ensemble-based Neural Networks","authors":"Ziying Yang, Jiping Liu, Chaoyuan Yang, Yongyun Hu","doi":"10.1175/jtech-d-22-0066.1","DOIUrl":null,"url":null,"abstract":"\nSea 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 layers (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 forecasted SST substantially by 0.35°C (0.34°C) for the testing (training) data and ANN3 further reduces RMSE relatively by 0.49°C (0.47°C). Both the ensemble-based ANN1 and ANN3 can significantly reduce the spatial and temporal varying bias of the CFSv2 forecasted SST in the Pacific and Atlantic Oceans, and ANN3 shows better agreement with\nthe observation than that of ANN1 in some subregions.","PeriodicalId":15074,"journal":{"name":"Journal of Atmospheric and Oceanic Technology","volume":" ","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2023-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Atmospheric and Oceanic Technology","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1175/jtech-d-22-0066.1","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, OCEAN","Score":null,"Total":0}
引用次数: 0
Abstract
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 layers (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 forecasted SST substantially by 0.35°C (0.34°C) for the testing (training) data and ANN3 further reduces RMSE relatively by 0.49°C (0.47°C). Both the ensemble-based ANN1 and ANN3 can significantly reduce the spatial and temporal varying bias of the CFSv2 forecasted SST in the Pacific and Atlantic Oceans, and ANN3 shows better agreement with
the observation than that of ANN1 in some subregions.
期刊介绍:
The Journal of Atmospheric and Oceanic Technology (JTECH) publishes research describing instrumentation and methods used in atmospheric and oceanic research, including remote sensing instruments; measurements, validation, and data analysis techniques from satellites, aircraft, balloons, and surface-based platforms; in situ instruments, measurements, and methods for data acquisition, analysis, and interpretation and assimilation in numerical models; and information systems and algorithms.