GeoAI: a “high-tech” domain for ITC and the UT
In the geo community, the term “geoAI” is becoming more and more pervasive. The scientific field of geospatial artificial intelligence (geoAI) combines innovations in spatial science with the rapid growth of methods in AI and big data. It can be identified as a three-pillar: data-driven, knowledge-driven, and highlights geospatial applications. In terms of knowledge, there is particular attention to machine learning, deep learning, data mining, and high-performance computing to integrate meaningful information from spatial big data. In terms of big data, GeoAI pays attention to scalable and/or distributed processing and intelligent analysis.
GeoAI is highly interdisciplinary, bridging many scientific fields including geography, geosciences, computer science, and engineering. The innovation of geoAI also lies in its flexibility for applications to address real-world problems. GeoAI is thus an emergent spatial analytical framework for data-intensive Geographic information science, but it can also include smaller datasets in a wider context.
As a specific niche, spatial computing serves as an interesting concept for technological innovation. It addresses the integration of different computing environments: from observation to computer-aided design and decision-making. It links information collected at different scales and from different sources, going beyond what virtual and augmented reality can achieve today. Applications so far have addressed indoor mapping, through outdoor mapping towards overviews of neighborhoods and urban areas. Similar integrations potentially apply to vegetation, disaster management, agriculture, health and water-oriented studies.