BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//GoGeomatics - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:GoGeomatics
X-ORIGINAL-URL:https://gogeomatics.ca
X-WR-CALDESC:Events for GoGeomatics
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Toronto
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Toronto:20250925T130000
DTEND;TZID=America/Toronto:20250925T140000
DTSTAMP:20260609T224258
CREATED:20250922T205527Z
LAST-MODIFIED:20250922T205538Z
UID:241572-1758805200-1758808800@gogeomatics.ca
SUMMARY:Canadian Space Agency’s Webinar: Use of Artificial Intelligence for Earth Observation
DESCRIPTION:The Canadian Earth observation community and people curious about space-based remote sensing are invited to join the upcoming Canadian Space Agency’s (CSA) Earth Observation (EO) in Orbit webinar on the theme of the use of  artificial intelligence for Earth Observation. \nPresentation 1: On-Board ML in Resource-Constrained Satellites: Challenges and Pathways Forward\n\nDate: September 25\, 2025\nTime: 13:00 to 13:30 EDT\nPlace: Online\nLanguage: In English (captions and visual content will be available in French)\nPresented by: Benjamin Chui\, VP\, Systèmes définis par logiciel\, GALAXIA\n\nTheme\nCritical Earth Observation missions rely on timely analysis to support decision-making and response coordination in disaster monitoring\, resource management\, climate change tracking\, and defence. Historically\, when it comes to EO-related Machine Learning\, raw data is downlinked and processed on the ground\, introducing delays and limiting the impact that responses can have. Deploying ML models directly onboard satellites and downlinking only the results represents a transformative shift in how we detect and deal with critical events. \nCubeSats represent an excellent candidate for performing critical EO-related ML at scale\, allowing for low-cost\, highly distributed\, and responsive sensing. However\, the constrained size\, power budget\, and computational capacity of CubeSats introduce their own suite of challenges that must be addressed. Overcoming these challenges will determine how far we can push the boundaries of in-orbit autonomy and how quickly we can turn raw EO data into actionable insights. \nClick here to join the meeting \nPresentation 2: Robust & Reliable Onboard AI for Space\n\nDate: September 25\, 2025\nTime: 13:30 to 14:o0 EDT\nPlace: Online\nLanguage: In English (captions and visual content will be available in French)\nPresented by: Andrew Macdonald\, Director\, AI & Autonomy\n\nTheme\nThe space environment is becoming more complex\, with more commercial and government entities operating new mission types from low earth orbit to the lunar surface. These missions face a challenge\, generating vast amounts of data that cannot necessarily be brought back to the ground in time to make key decisions. Onboard machine learning (ML) algorithms can address this challenge\, opening up faster decision cycles and new capabilities\, but only if they can be verified and validated for mission critical applications. \nFor the past decade\, Mission Control has developed AI algorithms and applications deployed to satellite EO and lunar robotic missions\, developed deployment tools and software verification and validation techniques for deploying AI on low-SWAP processors for space\, and developed methods to monitor and update the performance of ML algorithms onboard. In this talk will discuss the lessons learned and challenges of implementing ML models at the edge in space\, including use cases from Mission Control’s past and upcoming lunar flight missions and never before seen commissioning photos from its Mission Persistence satellite\, which launched in June 2025. \nNote: The presentations will be in the language of choice of the presenter\, and automated captions with simultaneous translation will be accessible. You can ask your questions in the official language of your choice at the end of each presentation. \nClick here to join the meeting
URL:https://gogeomatics.ca/event/canadian-space-agencys-webinar-use-of-artificial-intelligence-for-earth-observation/
LOCATION:Online
END:VEVENT
END:VCALENDAR