BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//www.bayceer.uni-bayreuth.de//NONSGML kigkonsult.se iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:32376464-3435-4533-b139-363430353939
X-WR-CALNAME:BayCMS-Export
X-WR-CALDESC:This is a calendar exported from BayCMS
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
TZUNTIL:20280326T010000Z
BEGIN:STANDARD
TZNAME:CET
DTSTART:20251026T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20261025T030000
RDATE:20271031T030000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:CEST
DTSTART:20260329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RDATE:20270328T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:www.bayceer.uni-bayreuth.de-bayceer-t175491id
DTSTAMP:20260625T002854Z
DESCRIPTION:Deep learning (DL) bridges the gap between growing digital reso
 urces and data-intensive finescale evolutionary and ecological application
 s. The desired goal of DL is to capture both species-level and subtle popu
 lation-level genetic and morphological variation. Using Ranunculus auricom
 us as a model\, along with other species groups\, we demonstrate that DLne
 tworks can automatically extract phylogenetic signals from single-copy nuc
 lear genesequences to delimit species under complex evolutionary scenarios
 . The high dimensionalityof data representations (features) automatically 
 extracted by DL first required a dimensionreduction\, followed by species 
 clustering. We validated species classifications based on directcomparison
  to recently updated integrative taxonomies. Furthermore\, we quantitative
 lycompared state-of-the-art DL delimitation methods using cluster accuracy
  metrics.Analyzing morphological variation in Ranunculus auricomus\, we al
 so show that DL networkscan automatically extract intricate leaf shape tra
 its from images taken in situ and in herbaria\,and validate their taxonomi
 c relevance via geometric morphometrics. Looking ahead andmoving from limi
 ted sampling towards large-scale image data\, automated workflows for trai
 tcapture offer an efficient way to harness big data from global platforms 
 like GBIF. We show afew examples of accelerating the extraction of functio
 nal plant traits&mdash\;such as flower color inalpine gentians or leaf dis
 section indices in European trees&mdash\;for opening new possibilities ofh
 igh-throughput phenotyping to help us to better understand large-scale mac
 roecologicalpatterns.Ultimately\, deep learning introduces an objective\, 
 reproducible standard to speciesdelimitation\, which can rapidly accelerat
 e the discovery and revision of plant diversityworldwide. AI approaches to
  uncover fine-scale variation in plant phylogenomics and phenotypic traits
DTSTART;TZID=Europe/Berlin:20260611T000000
DTEND;TZID=Europe/Berlin:20260611T235959
SUMMARY:Dr. Kevin Karbstein and Dr. Ladislav Hodac\, University of Jena and
  MPI Ilmenau: AI approaches to uncover fine-scale variation in plant phylo
 genomics and phenotypic traits
TRANSP:TRANSPARENT
END:VEVENT
END:VCALENDAR