BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Signal Processing and Data Science in Earth Observation - Xiaoxian
 g Zhu (Technical University of Munich and German Aerospace Center)
DTSTART:20180713T100000Z
DTEND:20180713T110000Z
UID:TALK108121@talks.cam.ac.uk
CONTACT:Carola-Bibiane Schoenlieb
DESCRIPTION:Geoinformation derived from Earth observation satellite data i
 s indispensable for many scientific\, governmental and planning tasks. Car
 tography\, geophysics\, resource management\, civil security\, disaster re
 lief\, as well as for planning and decision support are just a few example
 s. Therefore\, the European Commission operates the Copernicus program tha
 t guarantees the future free access to remote sensing data delivered by Se
 ntinels\, a new fleet of ESA satellites. Germany also operates Earth obser
 vation satellites with so far the highest technical quality\, including th
 e current TerraSAR-X and TanDEM-X and the future EnMAP\, DESIS and Tandem-
 L missions.\n\nCan modern signal processing and machine learning algorithm
 s improve information retrieval from remote sensing data\, and hence take 
 advantage of this precious satellite infrastructure more efficiently? In t
 his seminar\, several modern signal processing and machine learning concep
 ts\, including compressive sensing\, nonlocal filters\, robust estimators 
 and deep learning\, are proposed for solving diverse scientific problems i
 n remote sensing including radar and optical (multispectral and hyperspect
 ral) technologies. A particular focus will be put on data fusion\, which h
 as shown an ever-growing relationship with remote sensing. The presented c
 oncepts are not only supposed to substantially improve information retriev
 al from existing sensors but also contribute to the preparation and the de
 sign of the next-generation Earth observation satellite missions. In addit
 ion\, a showcasing geoscience application – global urban mapping – wil
 l be highlighted.\n\n\n\nBiography:\n\nXiaoxiang Zhu is the professor for 
 Signal Processing in Earth Observation (SiPEO\, www.sipeo.bgu.tum.de) at T
 echnical University of Munich (TUM) and the German Aerospace Center (DLR)\
 , Germany. She is also the founding head of the department of EO Data Scie
 nce in DLR’s Earth Observation Center. \n\nZhu received the Master (M.Sc
 .) degree\, her doctor of engineering (Dr.-Ing.) degree and her “Habilit
 ation” in the field of signal processing from TUM in 2008\, 2011 and 201
 3\, respectively. She was a guest scientist or visiting professor at the I
 talian National Research Council (CNR-IREA)\, Naples\, Italy\, Fudan Unive
 rsity\, Shanghai\, China\, the University of Tokyo\, Tokyo\, Japan and Uni
 versity of California\, Los Angeles\, United States in 2009\, 2014\, 2015 
 and 2016\, respectively. Her main research interests are remote sensing an
 d Earth observation\, signal processing\, machine learning and data scienc
 e\, with a special application focus on global urban mapping.
LOCATION:MR 5\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR