BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.33.0//EN
X-ORIGINAL-URL:https://essic.umd.edu/
X-WR-CALNAME:ESSIC
X-WR-CALDESC:UMD - Earth System Science Interdisciplinary Center
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T010000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-f9d81ff01aec9a8625983fe8f5c382f0@essic.umd.edu
DTSTART;TZID=America/New_York:20230403T140000
DTEND;TZID=America/New_York:20230403T150000
DTSTAMP:20230905T131254Z
CREATED:20230905
LAST-MODIFIED:20230905
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:Improving Climate Models Using Corrective Machine Learning vs. Other Emulation Approaches
DESCRIPTION:Dr. Chris Bretherton’s seminar flyer\nDr. Christopher Bretherton\nSenior Director of Climate Modeling\nAllen Institute for Artificial Intelligence (AI2)\nMonday April 3, 2023, 2 PM ET\n \nAbstract:\nAI2, with GFDL, has developed a corrective machine learning (ML) methodology to improve weather forecast skill and reduce climate biases in a computationally efficient coarse-grid climate model.  The corrective ML is trained by nudging the 3D temperature, humidity and wind fields forecast by the coarse-grid model to a time-dependent global reference and learning the ‘nudging tendencies’ as a function of the column state of the model.  The reference can be a reanalysis (for present-climate simulation) or a finer-grid version of the same model that may be more trustworthy across a range of climates. The ML is interpreted as a correction to the combined physics parameterizations of the coarse-grid model.  We trained the ML on global 25 km simulations in multiple climates, and separately on a year-long 3 km simulation, and applied it in 200 km coarse-grid simulations.  The ML reduced annual-mean land temperature and precipitation pattern biases by up to 50% and enhanced weather forecast skill.  We compare strengths and weaknesses of this method vs. other strategies for emulating reference climate models, including another hybrid approach using reservoir computing, and full model emulation.\n \nBiosketch:\nChris Bretherton directs a climate modeling group at AI2 in Seattle which uses machine learning trained on global storm-resolving model output and observational data to improve climate model simulations.  He is an Emeritus Professor of the Atmospheric Science and Applied Mathematics Departments at the University of Washington, where for 35 years he studied cloud formation and turbulence and improved their simulation in atmospheric models.  He is an American Meteorological Society Charney Award winner, IPCC author, AMS and AGU Fellow, and a member of the National Academy of Sciences.\n \nWebinar:\nEvent site: https://go.umd.edu/bretherton ( https://go.umd.edu/bretherton )\nZoom Webinar: https://go.umd.edu/brethertonwebinar ( https://go.umd.edu/brethertonwebinar )\nZoom Meeting ID:\nZoom password: essic\nUS Toll: +13017158592\nGlobal call-in numbers: https://umd.zoom.us/u/aMElEpvNu ( https://umd.zoom.us/u/aMElEpvNu )\nFor IT assistance:\nCazzy Medley: cazzy@umd.edu ( mailto:cazzy@umd.edu )\nResources:\nSeminar schedule & archive: https://go.umd.edu/essicseminar ( https://go.umd.edu/essicseminar )\nSeminar Google calendar: https://go.umd.edu/essicseminarcalendar ( https://go.umd.edu/essicseminarcalendar )\nSeminar recordings on Youtube: https://www.youtube.com/user/ESSICUMD ( https://www.youtube.com/user/ESSICUMD )\n
URL:https://essic.umd.edu/events/improving-climate-models-using-corrective-machine-learning-vs-other-emulation-approaches/
CATEGORIES:Spring 2023
ATTACH;FMTTYPE=image/png:https://essic.umd.edu/wp-content/uploads/2023/09/headshot_Chris.Bretherton.png
END:VEVENT
END:VCALENDAR