BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.3.1//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:319@escience.washington.edu
DTSTART;TZID=America/Los_Angeles:20260219T163000
DTEND;TZID=America/Los_Angeles:20260219T172000
DTSTAMP:20260129T215556Z
URL:https://escience.washington.edu/events/uw-data-science-seminar-miles-e
 pstein/
SUMMARY:UW Data Science Seminar: Miles Epstein
DESCRIPTION:Please join us for a UW Data Science Seminar featuring UW Atmos
 pheric and Climate Science PhD student Miles Epstein on Thursday\, Februar
 y 19th from 4:30 to 5:20 p.m. PT. The seminar will be held in IEB G109.\n\
 n&nbsp\;\n"Predicting Biases in Day 1 Probabilistic Convective Outlooks fr
 om Time-Evolving Environmental Conditions with Convolutional Neural Networ
 ks"\nAbstract: Severe thunderstorms (those producing straight-line winds a
 t least 58 mph\, hail at least one inch in diameter\, and/or a tornado) po
 se a substantial threat to life and property in the United States. To help
  mitigate these risks\, the National Oceanic and Atmospheric Administratio
 n/National Weather Service’s Storm Prediction Center issues daily Convec
 tive Outlooks (COs) outlining spatial risk levels for severe thunderstorms
  with up to eight days of lead time. Previous work (in review) details two
  methods for evaluating probabilistic COs\; this work quantifies day-level
  biases in total storm coverage and in location (broken into north–south
  and east–west components) for Day 1 probabilistic Convective Outlooks.\
 n\nWe train a Convolutional Neural Network (CNN) to predict the probabilis
 tic Sinh-arcsinh-normal (SHASH) distribution for coverage bias and both co
 mponents of directional bias in Day 1 probabilistic Convective Outlooks fr
 om time-evolving\, gridded environmental data (via Fifth Generation ECMWF 
 Atmospheric Reanalysis (ERA5)). The trained model may be used operationall
 y by inputting modeled environmental conditions (e.g.\, with one or two da
 ys of lead time). The distributions predicted by the model provide “anti
 cipated feedback” and quantify expected uncertainty for Convective Outlo
 oks associated with those conditions. Ultimately\, by better understanding
  the environments in which severe thunderstorms develop\, we can issue mor
 e accurate outlooks that will best mitigate loss of life and damage caused
  by those storms.\n\n&nbsp\;\n\nSpeaker Bio: Miles Epstein is a PhD studen
 t in the Department of Atmospheric and Climate Science at the University o
 f Washington. His research focuses on improving forecasts for severe thund
 erstorms and other high-impact weather events with data-driven methods\, p
 articularly machine learning.\n\n&nbsp\;\n\n\nThe 2025-2026 seminars will 
 be held in person\, and are free and open to the public.\n\n
ATTACH;FMTTYPE=image/jpeg:https://escience.washington.edu/wp-content/uploa
 ds/2026/01/image001-scaled.jpg
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR