BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//scipy-2026//talk//N9YDEL
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-scipy-2026-N9YDEL@pretalx.com
DTSTART;TZID=CST:20260715T143500
DTEND;TZID=CST:20260715T150500
DESCRIPTION:The advent of multimodal large language models (mLLMs) provides
  new opportunities for automated data exploration tasks on multi-petabyte 
 atmospheric data sets. In this presentation\, we present Nepho\, a Python 
 package for parallel mLLM prompting on collections of atmospheric quickloo
 k data plots. We then evaluate the accuracy of several mLLMs in answering 
 questions about Atmospheric Radiation Measurement (ARM) atmospheric datase
 ts. We demonstrate that the GPT 4/5 and llama3-vision models were the most
  accurate models for quicklook plot exploration and recommend prompt engin
 eering and retrieval-augmented generation for such data exploration workfl
 ows.
DTSTAMP:20260715T022753Z
LOCATION:Thomas Swain Room
SUMMARY:Nepho: A workflow for using mLLMs for atmospheric data plot explora
 tion - Bobby Jackson
URL:https://pretalx.com/scipy-2026/talk/N9YDEL/
END:VEVENT
END:VCALENDAR