BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.5//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:381@escience.washington.edu
DTSTART;TZID=America/Los_Angeles:20261027T163000
DTEND;TZID=America/Los_Angeles:20261027T172000
DTSTAMP:20261020T005433Z
URL:https://escience.washington.edu/events/uw-data-science-and-ai-seminar/
SUMMARY:UW Data Science and AI Seminar: Kaeli Swift
DESCRIPTION:\nPlease join us for a UW Data Science Seminar featuring UW Res
 earch Scientist Kaeli Swift on Tuesday\, October 27th from 4:30 to 5:20 p.
 m. PT. The seminar will be held in HCK 132.\n“Machine learning Megapodes
 : Our journey from shaved yaks to analyzed acoustic tracks ”\nAbstract:T
 he Commonwealth of the Mariana Islands (CNMI) is a small archipelago locat
 ed in the Western Pacific. Like other island systems\, the Marianas are ho
 me to several endemic and rare species. Our work primarily concerned the d
 evelopment of an avian acoustic monitoring system that will be used on Tin
 ian Island to detect for the presence of the Micronesian megapode (Megapod
 ius laperouse laperouse)\, a federally endangered ground bird. Tinian\, a 
 small island and home to a growing US military base\, was likely occupied 
 historically by megapodes\, however\, megapodes have not been detected the
 re since 2020. Bioacoustic monitoring offers promising utility for the lar
 ge-scale monitoring of rare species\, but presents technical challenges fo
 r ecologists who lack robust programming backgrounds to implement post-pro
 cessing algorithms to review large datasets of acoustic recordings. We had
  two specific aims while working with the Accelerator program: 1) to under
 stand and produce a deep learning classifier capable of detecting for the 
 presence of megapodes with a minimal false negative rate and 2) to learn b
 est practices for and develop better data management and processing pipeli
 nes. At the onset of the program\, we had already acquired and labeled ove
 r 800 clips representing the four different call types produced by megapod
 es\, in addition to thousands of other clips representing the common bioti
 c and abiotic sounds of Tinian. Through our collaboration with Spencer Woo
 d and Vaughn Iverson\, we successfully ground tested the development of me
 gapode classifiers using OpenSoundscape\, a Python utility library\, and B
 irdNET\, an open-source AI-powered bioacoustics analyzer. Our ability to s
 uccessfully utilize these programs\, however\, required learning a number 
 of support programs including Git\, Docker\, Linux\, UW Hyak\, and Python.
  Here we will discuss our experience navigating the growing field of AI-po
 wered bioacoustics monitoring from the perspective of wildlife ecologists.
 \n\nSpeaker Bio:Kaeli Swift is a research scientist with the University of
  Washington. For the past 5 years she has lived and worked on the remote i
 sland of Tinian\, where she studies the ecology of endemic forest birds. S
 he received her PhD from the University of Washington where she studied cr
 ow funerals.\n\n\nThe 2026-2027 seminars will be held in person\, and are 
 free and open to the public.\n\n\n\n\n\n\n
ATTACH;FMTTYPE=image/jpeg:https://escience.washington.edu/wp-content/uploa
 ds/2026/10/IMG_9612-2-1-scaled.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