Over the past 50 years, geographers have embraced each new technological shift in geographic information systems (GIS) - the technology that turns location data into maps and insights about how places and people interact - first the computer boom, then the rise of the internet and data-sharing capabilities with web-based GIS, and later the emergence of smartphone data and cloud-based GIS systems. Now, another paradigm shift is transforming the field: the advent of artificial intelligence (AI) as an independent "agent" capable of performing GIS functions with minimal human oversight.
In a study published in Annals of GIS, a multi-institutional team led by geography researchers at Penn State built and tested four AI agents in order to introduce a conceptual framework of autonomous GIS and examine how this shift is redefining the practice of GIS.
"Just like the paradigm shifts of the past, autonomous GIS represents an emerging paradigm of integrating AI with GIS, where it is not just another tool but instead becomes an artificial geospatial analyst able to use GIS tools to solve geospatial problems," said lead author Zhenlong Li, associate professor of geography in the College of Earth and Mineral Sciences and director of the Geoinformation and Big Data Research Lab.
"In this study, we spent time exploring, as a GIS community, how to best integrate AI 'agent' technology into existing GIS workflows, and analyze the current drawbacks and limitations of the systems," Li said. "Our goal is to lay the groundwork for the geospatial community to develop GIS systems that move beyond traditional workflows to autonomously reason, derive, innovate and advance geospatial solutions to pressing challenges."
With their four proof-of-concept AI-powered GIS agents, researchers demonstrated that the agents can retrieve geospatial data, perform spatial analysis and generate maps with minimal human intervention.
In one case study, the researchers built a data retrieval agent called LLM-Find, first detailed in the International Journal of Digital Earth, which automatically fetches geospatial datasets based on users' requests, such as "download road networks excluding footways and service ways for a school walkability assessment in Columbia, South Carolina." Within minutes, LLM-Find obtained data on sidewalks, road networks, school locations and high-resolution remote-sensing imagery needed for a complex assessment.
"LLM-Find demonstrated that autonomous GIS agents can handle data acquisition from sources without manual dataset hunting, helping to reduce the grunt work of data preparation in spatial analyses," Li said. "But the number of sources the AI agent can consult is still limited, so human oversight and management is needed for LLM-Find."
The next GIS agent that researchers built and tested, LLM-Geo, assessed school walkability using the data fetched by LLM-Find, then autonomously generated a spatial workflow that produced walkability scores and maps.
"This is a more complex task that goes beyond data retrieval, where the AI agent is actually doing analysis of data based on a plain-language prompt," Li explained. "This analysis work might normally be done by a junior or entry-level geographer."
The next case study, LLM-Cat, completed more rigorous cartographic tasks - going beyond data acquisition and analysis to design visual maps. The agent made decisions on symbols, color scales, map views and other map elements, bringing the whole system closer to full automation.
