Development of a hybrid ML and physical model global ensemble system

Details

• Personal Author:
  Wang, Jun ; Sadeghi Tabas, Sadegh ; Fu, Bing ; Cui, Linlin ; Zhang, Zhan ; Zhu, Lin ; Peng, Jiayi ; Carley, Jacob R.
• Corporate Authors:
  National Centers for Environmental Prediction (U.S.) ; Lynker. ; Axiom.
• NOAA Program & Office:
  NWS (National Weather Service) ; EMC (Environmental Modelling Center) ; NCEP (National Centers for Environmental Prediction)
• Description:
  Recently, data-driven machine learning weather prediction (MLWP) models not only produce superior forecasts compared to traditional numerical weather prediction (NWP) models but also run with magnitudes smaller computing resources and are significantly faster than traditional NWP. It opens new possibilities for creating large-size ensembles. In this study we explored several approaches to create an MLWP global ensemble system, including a hybrid ensemble system combining the MLWP ensemble with the operational NWP global ensemble.
• Keywords:
  Atmospheric Models Numerical Weather Forecasting Atmospheric Models Numerical Weather Forecasting
• Series:
  Office note (National Centers for Environmental Prediction (U.S.))   522
• DOI:
  https://doi.org/10.25923/7kpr-5e68
• Format:
  pdf
• Document Type:
  Office Note
• License:
  https://creativecommons.org/publicdomain/zero/1.0/
• Rights Information:
  CC0 Public Domain
• Compliance:
  Submitted
• Main Document Checksum:
  urn:sha-512:f673189198508f28a93fee4822646889e1b5e24cd4caff2f59b947f2f351ca4b49ecd0d7299a4d3e1d8548238532e72b0f3ed70b493df86ccc7debf1274f7121
• Download URL:
  https://repository.library.noaa.gov/view/noaa/70717/noaa_70717_DS1.pdf
• File Type:
  [PDF - 3.34 MB ]