Utilizing Artificial Intelligence for Geospatial Simulations and Cities: Opportunities and Challenges
Abstract: Geospatial simulations have been developed to explore a wide range of phenomena over differ spatial and temporal scales ranging from the micro movement of pedestrians over seconds and hours to that of the macro movement of people over years. Generally speaking, the aim of such models is to gain a greater understanding of the world around us. Over time, such models have become more representative of the populations they seek to model due partially by increased computational power and the availability of data. However, challenges still exist in creating models and leveraging the universe of data to parametrize and validate them. Coinciding with the growth in geospatial simulations we are now witnessing a tremendous growth in artificial intelligence in all aspects of our daily lives which is also transcending into geospatial modeling. Using cities as application domain, this presentation will explore how AI and large language models in particular, can be used in various aspects of the geospatial modeling process. Cities are chosen as the domain as they now provide homes for more people than ever before, and with more and more people living in cities achieving sustainable cities is crucial for the betterment of all. However, I will also argue that AI alone is not the panacea when it comes to archiving urban sustainability nor higher fidelity geospatial models and many challenges exist and the talk with conclude with these.