Corey K Potvin (@corey_potvin) profile picture

Corey K Potvin

@corey_potvin

Research Meteorologist at NOAA National Severe Storms Laboratory.

nssl.noaa.gov/users/potvin/public_html/
Joined February 2020
  • Tweets142
  • Following106
  • Followers142
2Media
Photo by Corey K Potvin (@corey_potvin)Photo by Corey K Potvin (@corey_potvin)
In EOR at @AMS_AIES: "Using machine learning to predict convection-allowing ensemble forecast skill: Evaluation with the NSSL Warn-on-Forecast System" doi.org/10.1175/AIES-D-23-01…
2
2
192
Huge kudos to @MontePhD for leading this awesome work! AI will undoubtedly play a major role in NWP at all scales.
Montgomery Flora, Ph.D. (@MontePhD) profile pictureMontgomery Flora, Ph.D.@MontePhD9 Sep 2024
🚨 Exciting Announcement! 🚨 Introducing WoFSCast: our AI-powered system for predicting thunderstorm evolution at watch-to-warning scales. 🌩️⚡ essopenarchive.org/users/829…
4
239
Our paper combining AI/ML, storm-scale ensemble prediction, and "forecasting forecast skill" is now in final form in @AMS_AIES: doi.org/10.1175/AIES-D-23-01… Co-authors: @MontePhD, Patrick Skinner, @tonyreinhart, @BrianWxFLA
1
4
371
Please share!
Corey K Potvin (@corey_potvin) profile pictureCorey K Potvin@corey_potvin3 Jan 2024
The Feb 1 deadline for NRC postdoc apps is coming up! I am looking for someone to work with me on a topic related to our Warn-on-Forecast System. Search "Potvin" at ra.nas.edu/RAPLab10/Opportun…. These project descriptions are flexible. Possible topics in next post....
89
The Feb 1 deadline for NRC postdoc apps is coming up! I am looking for someone to work with me on a topic related to our Warn-on-Forecast System. Search "Potvin" at ra.nas.edu/RAPLab10/Opportun…. These project descriptions are flexible. Possible topics in next post....
1
3
2
5
1,751
Possible NRC postdoc topics: (1) WoFS forecast emulation via deep learning (2) Other ML applications (3) Thunderstorm predictability (4) Multi-resolution ensemble design (5) Novel verification techniques (6) ??? Feel free to reach out here or at [email protected].
129
Where can I find a table of U.S. raob sites with 3-letter IDs and lats/lons?
1
187
Registration is open for the *free*, virtual 5th NOAA AI Workshop (19-21 Sept): noaa.gov/ai/events/5th-noaa-…

5th NOAA AI Workshop (2023)

September 19-21, 2023: 5th NOAA AI Workshop on Leveraging Artificial Intelligence in Environmental Sciences , Video recordings offsite link available for sessions (click on "Watch Recording") Opening...

noaa.gov
1
67
After having #ChatGPT write code for you, don't forget to also have it write a poem about the code.
3
148
New in JAMC: doi.org/10.1175/JAMC-D-21-02… 1. Our Bayesian model estimates that for every significant tornado recorded within the central U.S. during 1975-2019, 2 more tornadoes capable of significant damage occurred but were unreported or (more likely) underrated due to lack of DIs.

Improving Estimates of U.S. Tornado Frequency by Accounting for Unreported and Underrated Tornadoes

Abstract Many tornadoes are unreported because of lack of observers or are underrated in intensity, width, or track length because of lack of damage indicators. These reporting biases substantially...

journals.ametsoc.org
2
10
4
48
2. Nearly half of tornadoes go unrecorded at present, with little sign of improvement over the last decade. 3. Annual central U.S. tornado frequency has changed little since 1975.
1
1
4
Much gratitude to my collaborators! I think this algorithm would be valuable to a wide range of storm-scale applications. Monte Flora (@MontePhD) has a user-friendly version available at github.com/WarnOnForecast/Mo….
This Post is from an account that no longer exists. Learn more
1
New JTECH EOR: doi.org/10.1175/JTECH-D-21-0… New storm ID & classification algorithm tested on WoFS and MRMS data. Storm mode classifications consistent with experts' labels of 400 storms. Identifies cluster- and QLCS-embedded cells that many storm ID methods would miss.
1
2
Many thanks to coauthors Burkely Gallo, @tonyreinhart, Brett Roberts (@brettjrob), @pat_skinner_00, Ryan Sobash (@sobphd), Katie Wilson, Kelsey Britt (@KelsCBritt), Chris Broyles, Monte Flora (@MontePhD), Will Miller, and Claire Satrio!
New EOR paper in JAMC! doi.org/10.1175/JAMC-D-21-02… Co-authors: Chris Broyles, Pat Skinner (@pat_skinner_00), Harold Brooks (@hebrooks87). Highlights:

Improving Estimates of U.S. Tornado Frequency by Accounting for Unreported and Underrated Tornadoes

Abstract Many tornadoes are unreported because of lack of observers or are underrated in intensity, width, or track length because of lack of damage indicators. These reporting biases substantially...

journals.ametsoc.org
1
3
1
19
1. Our Bayesian model estimates that for every significant tornado recorded within the central U.S. during 1975-2019, 2 more tornadoes capable of significant damage occurred but were unreported or (more likely) underrated due to lack of damage indicators.
1
3
Well done, Nathan!
Montgomery Flora, Ph.D. (@MontePhD) profile pictureMontgomery Flora, Ph.D.@MontePhD4 Feb 2022
And he was awarded an outstanding student poster award! Congrats @Erickson_WX ! Top-level work out of this student!
Now in final form at doi.org/10.1175/WAF-D-21-007…
Corey K Potvin (@corey_potvin) profile pictureCorey K Potvin@corey_potvin4 Jan 2022
New WAF EOR by Will Miller: “Exploring the Usefulness of Downscaling Free Forecasts from the Warn-on-Forecast System”. doi.org/10.1175/WAF-D-21-007…
1
2
New WAF EOR by Will Miller: “Exploring the Usefulness of Downscaling Free Forecasts from the Warn-on-Forecast System”. doi.org/10.1175/WAF-D-21-007…
1
2
2
8
Running forecasts at 1.5-km (vs. 3-km) grid spacing led to improved forecasts of mid-level mesocyclones and, to a lesser extent, low-level mesocyclones. Lots of sophisticated CAM verification techniques used in this paper. Check it out!
1
We likely just got grazed by a weak tornado at our house in NE Norman. But the tornadic winds would have been counter to, and not much stronger than, the background flow, potentially *decreasing* the total wind here.
5
Check out this awesome paper from Monte Flora! Look for these and future Warn-on-Forecast ML products in the next few HWT Spring Forecasting Experiments.
Montgomery Flora, Ph.D. (@MontePhD) profile pictureMontgomery Flora, Ph.D.@MontePhD30 Apr 2021
Our paper on using #MachineLearning to calibrate Warn-on-Forecast System forecasts for severe weather hazards is in final form! This system will be evaluated during a next-day SFE activity. journals.ametsoc.org/view/jo…
2
I'm biased, but this is a very strong paper showcasing some really useful verification techniques for convection-allowing models.
This Post is from an account that no longer exists. Learn more
2
This just occurred to me while reviewing grad student applications: What a shame that their parents never get to see these glowing letters of recommendation! What pride they would feel!
1
8
I very much look forward to continuing to work with Dr. Flora on this important and exciting project!
Montgomery Flora, Ph.D. (@MontePhD) profile pictureMontgomery Flora, Ph.D.@MontePhD16 Dec 2020
I am proud to announce I have accepted a post-doc position at @OUCIMMS working with @corey_potvin! We will continue to improve short-term severe weather probabilistic guidance using machine learning (including deep learning) and Warn-on-Forecast output.
1
Load more