Published May 24, 2021 | Version 1

Supporting data for Xu et al. 2021 - Weather and Forecasting

  • 1. Pacific Northwest National Laboratory
  • 2. Colorado State University

Description

This is the dataset underpinning the paper "Deep Learning Experiments for Tropical Cyclone Intensity Forecasts" submitted to the journal Weather and Forecasting in 2021. 

24-hour model data used in LOYO testing (before scaling):
`NOAA_reanalysis_vars_global_w_dvs24.csv`
`NOAA_operational_vars_global_w_dvs24.csv`

24-hour model data used in LOYO testing (after scaling):
`train_global_fill_REA_na_wo_img_scaled.csv`

2019 operational data reserved for 24-hour model independent test:
`NOAA_operational_vars_global_wLabels_fill_na_Y2019.csv`

2020 operational data reserved for 24-hour model independent test:
`NOAA_operational_vars_global_wLabels_fill_na_Y2020.csv`

6-hour model data used in LOYO testing (before scaling):
`NOAA_reanalysis_vars_global_w_dvs6.csv`

Notes

The operational forecast portion of this research was supported by the Deep Science Agile Initiative at Pacific Northwest National Laboratory (PNNL). It was conducted under the Laboratory Directed Research and Development Program at PNNL. PNNL is a multiprogram national laboratory operated by Battelle for the U.S. Department of Energy under contract DE‐AC05‐76RL01830. The synthetic tropical cyclone portion of this research was supported by the Multisector Dynamics program areas of the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research as part of the multi-program, collaborative Integrated Coastal Modeling (ICoM) project.

Files

NOAA_operational_vars_global_w_dvs24.csv

Files (988.0 MB)

Name Size
md5:611548a0a6276210df845751a5006184
21.0 MB Preview Download
md5:a9e2efc3d743b875de21de3b089bcee0
3.9 MB Preview Download
md5:42f05a7e4813a73f11de9b537b8c47b9
6.8 MB Preview Download
md5:cab2987862e332605b5b5de0d319682b
277.1 MB Preview Download
md5:05c52878d2ca035ca3555738796b5933
287.7 MB Preview Download
md5:64b1489c5d695e360cabe235e100b14e
391.6 MB Preview Download