BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220812T074334Z
LOCATION:Foyer 2nd Floor
DTSTART;TZID=Europe/Stockholm:20220628T090000
DTEND;TZID=Europe/Stockholm:20220628T110000
UID:submissions.pasc-conference.org_PASC22_sess181_pos117@linklings.com
SUMMARY:P08 - Data-Driven Analysis of the Elder Problem Using Big Data and
Machine Learning
DESCRIPTION:Poster\n\nP08 - Data-Driven Analysis of the Elder Problem Usin
g Big Data and Machine Learning\n\nKhotyachuk, Johannsen\n\nIn this work,
the d3f software is used for numerical solving the problems in Computation
al Fluid Dynamics. We have ported the d3f software to the Spark cluster. S
uch a modification allowed implementing the mass parallel runs of d3f soft
ware, efficient post-processing, and further analysis of vast amounts of d
ata using Big Data tools and Machine Learning approaches. Specifically, ou
r Spark-d3f setup is used to simulate and analyze the Elder problem. For t
his problem, we achieved the following scientific results.
- Investi
gated the steady-state solutions of the Elder problem with regards to the
Rayleigh numbers (Ra), grid sizes, perturbations, etc.
- Analyzed th
e complexity of solutions regarding time, solution types, and other factor
s.
- Created a tool for visual exploration of large solution ensembl
es of the Elder problem.
- Developed predictive models for the Elder
problem using different classification methods.
Our predictive model
s are divided into three types, depending on how we designed the model's p
redictors (features). The best of them can predict a steady-state of the E
lder problem (i.e., when time t > 50 years) with 95% accuracy at
t=8-9 years.
END:VEVENT
END:VCALENDAR