BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.2//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:330@escience.washington.edu
DTSTART;TZID=America/Los_Angeles:20260401T163000
DTEND;TZID=America/Los_Angeles:20260401T172000
DTSTAMP:20260423T203108Z
URL:https://escience.washington.edu/events/uw-data-science-seminar-hernan-
 querbes/
SUMMARY:UW Data Science Seminar: Hernán Querbes Duhart
DESCRIPTION:Please join us for a UW Data Science Seminar featuring UW Civil
  &amp\; Environmental Engineering Master's student Hernán Querbes Duhart 
 on Wednesday\, April 1st from 4:30 to 5:20 p.m. PT. The seminar will be he
 ld in IEB G109.\n"Evaluating the Impact of Precipitation Forcing on Machin
 e Learning Streamflow Modeling"\nAbstract: Uruguay relies heavily on hydro
 power\, with three dams along the Río Negro providing nearly half of the 
 country's electricity. Accurate streamflow modeling is therefore critical 
 for dam operations and energy reliability. Recently\, long short-term memo
 ry (LSTM) networks have emerged as a leading approach for streamflow model
 ing\, and large-sample datasets such as CARAVAN (which includes meteorolog
 ical forcings such as time-series for precipitation\, temperature\, radiat
 ion\, among others and static attributes of the basins) have enabled their
  global application. However\, CARAVAN's reanalysis-based precipitation ha
 s been shown to reduce models performance in the US compared to other loca
 l products. This study presents the evaluation of LSTM-based streamflow mo
 deling in Uruguay\, training and evaluating models across eleven basins in
  the Río Negro under four precipitation forcings: CARAVAN\, MSWEP\, CHIRP
 S\, and local rain gauges. It assesses how precipitation product choice in
 fluences model performance and how hydrological signatures change when pre
 cipitation products are combined as model inputs. Results provide insight 
 into the suitability of global precipitation datasets for data-driven stre
 amflow modeling in data-scarce regions\, with implications for water resou
 rces planning.\n\nSpeaker Bio:Hernán Querbes is a Master's student in the
  Department of Civil &amp\; Environmental Engineering at the University of
  Washington\, specializing in hydrology. He completed his undergraduate de
 gree in Chemical Engineering at Universidad de la República (Uruguay) in 
 2023. His current research focuses on the application of machine learning 
 techniques\, specifically long short-term memory (LSTM) networks\, for str
 eamflow modeling.\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/2026/03/headshot-e1774550540118.jpg
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR