Key points are not available for this paper at this time.
Decision-makers in GIS often need to combine multiple spatial algorithms and operations to solve geospatial tasks. While professionals can understand and solve these tasks by using GIS tools sequentially, developing workflows for various tasks can be inefficient, as even slight differences in tasks require corresponding adjustments in the workflow. Recently, large language models (e.g., ChatGPT) presented a strong performance in semantic understanding and reasoning. Especially, AutoGPT can further extend the capabilities of large language models (LLMs) by automatically reasoning and calling externally defined tools. Inspired by these studies, we attempt to increase the efficiency of developing workflows for handling geoprocessing tasks by integrating the semantic understanding ability inherent in LLMs with mature tools within the GIS community. Specifically, we develop a new framework called GeoGPT that can conduct geospatial data collection, processing, and analysis in an autonomous manner. In this framework, a LLM is used to understand the demands of users, and then think, plan, and execute defined GIS tools sequentially to output final effective results. In this process, our framework is user-friendly, accepting natural language instructions as input and adapting to various geospatial tasks, which can serve as an assistant for GIS professionals. A systemic evaluation and several cases, including geospatial data crawling, spatial query, facility siting, and mapping, validate the effectiveness of our framework. Though limited cases are presented in this paper, GeoGPT can be further extended to various tasks by equipping with more GIS tools, and we think the paradigm of "foundational plus professional" implied in GeoGPT provides an effective way to develop next-generation GIS in this era of large foundation models.
Zhang et al. (Mon,) studied this question.