Repository logo
 

Forecast dataset associated with “From Random Forests to Flood Forecasts: A Research to Operations Success Story”

Simple item page
dc.contributor.authorSchumacher, Russ S.
dc.contributor.authorHill, Aaron J.
dc.contributor.authorKlein, Mark
dc.contributor.authorNelson, James A.
dc.contributor.authorErickson, Michael J.
dc.contributor.authorHerman, Gregory R.
dc.coverage.spatialContinental U.S.en_US
dc.coverage.temporal2018-03-15 to 2020-10-15 for day-2 and day-3 forecasts; 2019-03-15 to 2020-10-15 for day-1 forecasts.en_US
dc.date.accessioned2021-01-22T23:47:11Z
dc.date.available2021-01-22T23:47:11Z
dc.date.issued2021
dc.descriptionSchumacher, Hill, and Herman: Department of Atmospheric Science, Colorado State Universit; Klein, Nelson, and Erickson: NOAA Weather Prediction Center.
dc.descriptionGridded forecasts from the Colorado State University-Machine Learning Probabilities (CSU-MLP) system for excessive rainfall prediction over the continental United States. The dataset includes probabilistic forecasts for days 1, 2, and 3 from the 2017, 2019, and 2020 versions of the CSU-MLP forecast system. For the day 2 and 3 forecasts, daily forecasts are included from 19 June 2018 through 15 October 2020; for day-1 forecasts a period from 15 March 2019 through 15 October 2020 is used.en_US
dc.descriptionDepartment of Atmospheric Science
dc.description.abstractBecause excessive rainfall is poorly defined and difficult to forecast, there is a need for tools for Weather Prediction Center (WPC) forecasters to use when generating Excessive Rainfall Outlooks (EROs), which are issued for the contiguous United States at lead times of 1--3 days. To address this need, a probabilistic forecast system for excessive rainfall, known as the Colorado State University-Machine Learning Probabilities (CSU-MLP) system, was developed based on ensemble reforecasts, precipitation observations, and machine learning algorithms, specifically random forests. The CSU-MLP forecasts were designed to emulate the EROs, with the goal being a tool that forecasters can use as a ``first guess'' in the ERO forecast process. Resulting from close collaboration between CSU and WPC and evaluation at the Flash Flood and Intense Rainfall experiment, iterative improvements were made to the forecast system and it was transitioned into operational use at WPC. Quantitative evaluation shows that the CSU-MLP forecasts are skillful and reliable, and they are now being used as a part of the WPC forecast process. This project represents an example of a successful research-to-operations transition, and highlights the potential for machine learning and other post-processing techniques to improve operational predictions.en_US
dc.description.sponsorshipThis research and operational transition was supported by NOAA Joint Technology Transfer Initiative grants NA16OAR4590238 and NA18OAR4590378.en_US
dc.format.mediumPDF
dc.format.mediumZIP
dc.format.mediumNetCDF
dc.identifier.urihttps://hdl.handle.net/10217/222367
dc.identifier.urihttp://dx.doi.org/10.25675/10217/222367
dc.languageEnglishen_US
dc.language.isoengen_US
dc.publisherColorado State University. Librariesen_US
dc.relation.ispartofResearch Data
dc.relation.isreferencedbySchumacher, R. S., Hill, A. J., Klein, M., Nelson, J. A., Erickson, M. J., Trojniak, S. M., & Herman, G. R. (2021). From Random Forests to Flood Forecasts: A Research to Operations Success Story, Bulletin of the American Meteorological Society, 102(9), E1742-E1755. https://doi.org/10.1175/BAMS-D-20-0186.1en_US
dc.subjectweather predictionen_US
dc.subjectmachine learningen_US
dc.subjectprobabilistic forecastingen_US
dc.subjectexcessive rainfallen_US
dc.titleForecast dataset associated with “From Random Forests to Flood Forecasts: A Research to Operations Success Story”en_US
dc.typeDataseten_US

Files

Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
dataset_readme.pdf
Size:
85.98 KB
Format:
Adobe Portable Document Format
Description:
Download
No Thumbnail Available
Name:
Schumacher_202102_10217-222367.zip
Size:
840.13 MB
Format:
Zip File
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.05 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Research Data
Research Data