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:20250822T115807Z
LOCATION:Room 5.0B15 & 16
DTSTART;TZID=Europe/Stockholm:20250616T173000
DTEND;TZID=Europe/Stockholm:20250616T180000
UID:submissions.pasc-conference.org_PASC25_sess167_pap124@linklings.com
SUMMARY:iMagine: AI-Powered Image Data Analysis in Aquatic Science
DESCRIPTION:Elnaz Azmi, Khadijeh Alibabaei, and Valentin Kozlov (Karlsruhe
  Institute of Technology (KIT)); Álvaro López García (Instituto de Fisica 
 de Cantabria (IFCA), CSIC-UC); Dick Schaap (Mariene Informatie Service BV 
 (MARIS)); and Gergely Sipos (EGI Foundation)\n\nThe iMagine platform lever
 ages AI-driven tools to enhance the analysis of imaging data in marine and
  freshwater research, contributing to the study of ocean, sea, coastal, an
 d inland water health. Connected to the European Open Science Cloud (EOSC)
 , it enables the development, training, and deployment of AI models, colla
 borating with twelve aquatic science use cases to provide valuable insight
 s. The platform refines existing solutions from data acquisition and prepr
 ocessing to provide trained models as a service for users. iMagine outline
 s various AI-based tools, techniques, and methodologies for aquatic scienc
 e image processing, ensuring consistency and accuracy through clear annota
 tion guidelines and verified tools. The preparation of training datasets, 
 along with their metadata, ensures FAIRness and effective publishing in da
 ta repositories. Deep learning models, such as convolutional neural networ
 ks, are used for classification, object detection, and segmentation, with 
 performance metrics and evaluation tools ensuring reproducibility and tran
 sparency. AI model drift and data FAIRness are also explored, alongside ca
 se studies on AI challenges in aquatic sciences. By implementing these pra
 ctices, iMagine enhances data quality, promotes reproducibility, and foste
 rs scientific progress in aquatic research while collaborating with projec
 ts like AI4EOSC and Blue-Cloud. The platform allows users to develop, trai
 n, share, and serve AI models on its marketplace. The AI models are encaps
 ulated as Docker images and integrated with REST APIs to ensure their repr
 oducibility. Researchers benefit from the platform's flexibility, which en
 ables seamless execution of these Docker containers on both federated clou
 ds of the European Grid Infrastructure (EGI) and High-Performance Computin
 g (HPC) infrastructures.\n\nDomain: Climate, Weather, and Earth Sciences, 
 Computational Methods and Applied Mathematics\n\nSession Chair: Fawzi Moha
 med (ETH Zurich / CSCS)\n\n
END:VEVENT
END:VCALENDAR