A note on GeoAI from the perspective of geographical laws
Abstract
Recently, the rapid development of artificial intelligence has reshaped the research paradigm of many disciplines. Regarding geography, this trend is no exception. From the perspective of knowledge discovery, geographical research has two major tasks: revealing big unknowns and discovering laws. Artificial intelligence helps geographers discover knowledge or even automatically extract knowledge from these two aspects. Compared with other geoscience disciplines, geography focuses more on discovering “universal” laws. However, in the process of seeking geographical laws, we need to deal with the trade-off between universality and geographical heterogeneity, the core in which can be expressed as the theoretical foundation in artificial intelligence learning: generalization and interpretability. Therefore, there is an inherent logical consistency between the two disciplines. Introducing artificial intelligence to geographical studies will help to strengthen the disciplinary basis. This paper gives an example framework for artificial intelligence to discover geographical laws, and points out the future directions of geospatial artificial intelligence and geographic information science.
Hao Guo
Grad Student
2020 - present
My research interests lie in the general area of spatial analysis theory and methods, including spatial statistics, GeoAI, and spatial optimization.