Universität Wien
Achtung! Das Lehrangebot ist noch nicht vollständig und wird bis Semesterbeginn laufend ergänzt.

290107 SE Seminar aus Geoinformation: Geospatial Artificial Intelligence (GeoAI) (2023W)

5.00 ECTS (2.00 SWS), SPL 29 - Geographie
Prüfungsimmanente Lehrveranstaltung
Moodle

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 25 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

The course will take place in November. Details will follow.

  • Donnerstag 09.11. 13:00 - 16:00 Multimedia Mapping-Labor, NIG 1.Stock C0110
  • Freitag 10.11. 13:00 - 16:00 GIS-Labor Geo NIG 1.OG
  • Freitag 17.11. 13:00 - 16:00 GIS-Labor Geo NIG 1.OG
  • Donnerstag 23.11. 13:00 - 16:00 Multimedia Mapping-Labor, NIG 1.Stock C0110
  • Freitag 24.11. 13:00 - 16:00 GIS-Labor Geo NIG 1.OG
  • Donnerstag 30.11. 13:00 - 16:00 Multimedia Mapping-Labor, NIG 1.Stock C0110
  • Freitag 01.12. 13:00 - 16:00 Multimedia Mapping-Labor, NIG 1.Stock C0110

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

Geospatial Artificial Intelligence (GeoAI) is an advanced course (graduate-level) in spatial data science covering methods and techniques widely used in Cartography and Geoinformatics. The primary focus of this course is on geospatial data-driven modeling. We will introduce spatially explicit machine learning methods in geospatial AI, including spatial clustering, spatial autoregressive regression, geographically weighted regression and classification methods for geospatial data (e.g., georeferenced social media, GPS trajectories, and remote sensing images) and applications in various domains. We will also introduce spatial data processing methods and tools for getting geospatial data (in vector and raster formats) ready for machine learning workflows with Python programming.

Art der Leistungskontrolle und erlaubte Hilfsmittel

Upon completion of the course, you will be expected to:
· Understand concepts, methods, and techniques in spatial data science
· Be able to construct machine learning workflows on various types of geographic data
· Be familiar with Python programming for geospatial data processing
· Solve practical geospatial problems using machine learning and spatial analysis methods

Mindestanforderungen und Beurteilungsmaßstab

Assessment criteria: 40% Assignments + 40% Final Report + 20% Class Participation

Course grades will be based on literature reading or programming assignments (40% of total grade), one final project report (40% of total grade), and class participation including attendance and group discussion (20% of total grade). Assignments will require Python programming based on lecture materials.

Prüfungsstoff

A final brief report (4 pages including figures and maps):
Introduction
Data
Methods
Results and Discussions
References

Literatur

Books:
Song Gao, Yingjie Hu, Wenwen Li. (Eds) (2023) Handbook of Geospatial Artificial Intelligence. CRC Press.
Stan Openshaw, Christine Openshaw (1997) Artificial Intelligence in Geography. Wiley
Articles:
Song Gao. (2021) Geospatial Artificial Intelligence (GeoAI). Oxford Bibliographies in Geography. 1-16. DOI: 10.1093/OBO/9780199874002-0228
Krzysztof Janowicz, Song Gao, Grant McKenzie, Yingjie Hu. (2020) GeoAI: Spatially Explicit Artificial Intelligence Techniques for Geographic Knowledge Discovery and Beyond. International Journal of Geographical Information Science. 34(4), 625-636. DOI: 10.1080/13658816.2019.1684500

Zuordnung im Vorlesungsverzeichnis

(MK4-a-SE)

Letzte Änderung: Do 09.11.2023 10:28