BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:EO-AI4GlobalChange:  AI-Driven Earth Observation for Monitoring Gl
 obal Environmental Change - Yifang Ban\, Professor and Director\, Division
  of Geoinformatics  KTH Royal Institute of Technology  Associate Director\
 , Digital Futures  Stockholm\, Sweden  Lead\, GEO AI4EO Working Group
DTSTART:20260227T130000Z
DTEND:20260227T140000Z
UID:TALK241942@talks.cam.ac.uk
CONTACT:114742
DESCRIPTION:*Abstract*\n\nOur planet is facing unprecedented environmental
  challenges\, including rapid urbanization\, deforestation\, pollution\, b
 iodiversity loss\, and climate change. At the same time\, extreme events s
 uch as floods\, heatwaves\, and wildfires are increasing in frequency and 
 severity\, with far-reaching human\, economic\, and environmental impacts.
  Earth Observation (EO)\, combined with advances in Artificial Intelligenc
 e (AI)\, provides powerful tools for understanding these processes and sup
 porting evidence-based decision-making.\n\n\nIn this seminar\, Professor B
 an will discuss recent research at the intersection of EO and AI\, with a 
 focus on deep learning methods for monitoring environmental change at scal
 e. She will present selected results from EO-AI4GlobalChange\, a collabora
 tive research project developing novel\, globally-applicable deep learning
  approaches for analysing multi-sensor\, multi-modal EO data. The talk wil
 l cover examples including 2D and 3D urban mapping\, urban change detectio
 n\, wildfire detection and near-real-time monitoring\, flood mapping\, and
  multi-hazard building damage detection.\n\n\nThe seminar will also briefl
 y introduce PANGAEA\, a global benchmark for Geospatial Foundation Models\
 , and discuss insights from the systematic evaluation of widely used found
 ation models across multiple geospatial domains. Finally\, Professor Ban w
 ill briefly outline the objectives of the recently established AI4EO Worki
 ng Group within Group on Earth Observations (GEO)\, which aims to advance 
 GEO’s vision of Earth Intelligence for All through AI-driven Earth obser
 vation research\, innovation\, and collaboration.\n\n*Bio*\n\nDr. Yifang B
 an is the Professor and Director of the Division of Geoinformatics at KTH 
 Royal Institute of Technology\, and an Associate Director at Digital Futur
 es in Stockholm\, Sweden. Before joining KTH as a full professor in 2004\,
  Dr. Ban was a tenured Associate Professor at York University in Toronto\,
  Canada. She received her PhD in 1997 from the University of Waterloo in C
 anada. In 2023\, she earned a certificate in Leading Sustainability: High 
 Impact Leadership from the University of Cambridge.\n\n\nHer research has 
 been focused on Earth observation big data analytics\, machine learning/de
 ep learning for urban mapping\, urbanization monitoring and wildfire and f
 lood detection to support sustainable and resilient development. She has p
 ublished extensively on these topics and has been ranked by Stanford/Elsev
 ier among the World's top 2% of scientists in 2020-2025. Professor Ban is 
 Principal Investigator for a number of impactful projects\, including EO-A
 I4GlobalChange\, EO-AI4ResilientCities\, SAR4Wildfire\, and Climate Change
  Induced Disaster Management in Africa.\n\n\nProfessor Ban is the recipien
 t of the 2025 Group on Earth Observations (GEO) Lifetime Achievement Award
  and the 2023 Google Geo for Good Impact Award for her contributions to AI
 -driven Earth observation for disaster risk reduction and urban resilience
 . She serves as an invited expert to UN-Habitat on SDG indicators and as a
 n expert contributor to UNDRR\, leads the GEO AI4EO Working Group\, and is
  an Associate Editor of IEEE Transactions on Geoscience and Remote Sensing
 \, as well as a scientific committee member of major international remote 
 sensing conferences.\n\n
LOCATION:Room FW11 at the William Gates Building and on Zoom: https://cl-c
 am-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=ad
 don 
END:VEVENT
END:VCALENDAR