GIScience Colloquium The Science of GeoAI: Predictability, Explainability, and Reproducibility

  • Termin in der Vergangenheit
  • Montag, 12. Juni 2023, 10:15 Uhr
  • Geographisches Institut, Raum 004 (EG), Im Neuenheimer Feld 348, 69120 Heidelberg
    • Prof. Dr. Wenwen Li, Arizona State University (USA), School of Geographical Sciences and Urban Planning

AI, especially deep learning, has transformed many science and engineering disciplines because of its outstanding capabilities in learning and extracting patterns and knowledge in a data-driven manner. Geography is an ideal domain to extensively apply and further boost AI research because of its vast availability of diverse geospatial data, intriguing and complex human-environmental interactions, as well as its central role in enabling location-based analysis. In less than a decade, we have witnessed a rapidly growing interest and progress of GeoAI research – the transdisciplinary expansion of AI in geography and its sibling domains in urban, environmental, and social sciences.

This talk will review the series of GeoAI research conducted at Arizone State University, especially related to its applications in environmental analysis and natural feature detection. It involves the early attempts of improving the predictability of a GeoAI model and recent research in increasing its explainability and reproducibility to ensure trustworthy findings. The talk will also provide some reflections on the importance of sharpening the “science” of GeoAI in terms of its fundamental principles, theories, and methods to ensure its scientific rigor, liveliness, and long-lasting impacts.

Alle Termine der Veranstaltung 'GIScience Colloquium'