A Machine Learning-Based Bias Correction Method for Global Forecast System Products

Details

• Personal Author:
  Linlin Cui (https://orcid.org/0009-0000-7997-9845) ; Jun Wang (https://orcid.org/0009-0007-9030-3417) ; Sadegh Sadeghi Tabas (https://orcid.org/0000-0001-9157-3397) ; Jacob R. Carley (https://orcid.org/0000-0003-4763-6666)
• Corporate Authors:
  National Centers for Environmental Prediction (U.S.) ; Lynker. ; Axiom.
• NOAA Program & Office:
  NWS (National Weather Service) ; NCEP (National Centers for Environmental Prediction)
• Description:
  Accurate numerical weather forecasting is essential for forecasters to make predictions. However, operational forecast models often exhibit systematic biases. In this study, we present a machine learning-based approach called BC-Unet, a convolutional neural network (CNN) based on the renowned U-Net architecture, to correct biases in National Centers for Environmental Prediction (NCEP) operational Global Forecast System (GFS) v16 products over the contiguous United States (CONUS).
• Keywords:
  Machine Learning Numerical Weather Forecasting Machine Learning Numerical Weather Forecasting
• Series:
  Office note (National Centers for Environmental Prediction (U.S.))   520
• DOI:
  https://doi.org/10.25923/6266-e822
• Format:
  pdf
• Document Type:
  Office Note
• Place as Subject:
  United States
• License:
  https://creativecommons.org/publicdomain/zero/1.0/
• Rights Information:
  CC0 Public Domain
• Compliance:
  Submitted
• Main Document Checksum:
  urn:sha-512:e6bed60b5c9435b4bc4b4ebf540369e13689f34ffb6d73fdf0fc2fca86265847e603a0520fe3a26bd34aa7fcd718dd97e509814d590e891fd4dfb13b63f951bc
• Download URL:
  https://repository.library.noaa.gov/view/noaa/67181/noaa_67181_DS1.pdf
• File Type:
  [PDF - 2.57 MB ]