The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners.
As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.
i
A hybrid physics-machine learning model for orographic precipitation forecasting
-
2024
[PDF-1.04 MB]
Details:
-
Personal Author:
-
Corporate Authors:
-
NOAA Program & Office:
-
Description:The eXperimental System for High-resolution modeling for Earth-to-Local Domains (X-SHiELD; Harris et al. (2020); Cheng et al. (2022); Harris et al. (2023)) developed at the Geophysical Fluid Dynamics Laboratory (GFDL) is one of the frst models that has achieved realistic kilometer-scale global simulations (Stevens et al., 2019; Satoh et al., 2019). Furthermore, X-SHiELD has an advantage of being able to be run for multiple years and in diferent climates (Cheng et al., 2022; Harris et al., 2023; Bolot et al., 2023; Guendelman et al., 2024), providing valuable training data for machine learning (ML) applications (Bretherton et al., 2022; Kwa et al., 2023; Sanford et al., 2023; Watt-Meyer et al., 2024). This hybrid physics-ML model, developed jointly by the Allen Institute for Artifcial Intelligence and GFDL, is built upon a Python-wrapped (McGibbon et al., 2021) version of FV3GFS (UFS Community, 2020) and is part of the ai2cm/fv3net GitHub repository.
-
Keywords:
-
Series:
-
DOI:
-
Format:
-
Publisher:
-
Document Type:
-
Funding:
-
License:
-
Rights Information:CC0 Public Domain
-
Compliance:Submitted
-
Main Document Checksum:
-
Download URL:
-
File Type:
