Large Language Models (LLMs), such as ChatGPT, demonstrate a strong understanding of human natural language and have been explored and applied in various fields, including reasoning, creative writing, code generation, translation, and information retrieval. By adopting LLM as the reasoning core, we propose Autonomous GIS, an AI-powered geographic information system (GIS) that leverages the LLM's general abilities in natural language understanding, reasoning and coding for addressing spatial problems with automatic spatial data collection, analysis and visualization. We envision that autonomous GIS will need to achieve five autonomous goals including self-generating, self-organizing, self-verifying, self-executing, and self-growing. We introduce the design principles of autonomous GIS to achieve these five autonomous goals from the aspects of information sufficiency, LLM ability, and agent architecture. We developed a prototype system called LLM-Geo using GPT-4 API in a Python environment, demonstrating what an autonomous GIS looks like and how it delivers expected results without human intervention using two case studies. For both case studies, LLM-Geo successfully returned accurate results, including aggregated numbers, graphs, and maps, significantly reducing manual operation time. Although still lacking several important modules such as logging and code testing, LLM-Geo demonstrates a potential path towards next-generation AI-powered GIS. We advocate for the GIScience community to dedicate more effort to the research and development of autonomous GIS, making spatial analysis easier, faster, and more accessible to a broader audience.

翻译：大型语言模型（如ChatGPT）展现出对人类自然语言的强大理解力，并已在推理、创意写作、代码生成、翻译和信息检索等多个领域得到探索与应用。通过将LLM作为推理核心，我们提出自主式GIS——一种AI驱动的地理信息系统，它利用LLM在自然语言理解、推理和编码方面的通用能力，通过自动化的空间数据收集、分析与可视化来解决空间问题。我们设想自主式GIS需实现五项自主目标：自我生成、自我组织、自我验证、自我执行与自我成长。我们从信息充分性、LLM能力及智能体架构三个维度，阐述了实现这五项自主目标的设计原则。基于GPT-4 API在Python环境中开发的原型系统LLM-Geo，通过两个案例研究展示了自主式GIS的形态及其在无人工干预下交付预期结果的能力。两个案例中，LLM-Geo均成功返回精确结果（包括汇总数据、图表和地图），显著减少了人工操作时间。尽管仍缺乏日志记录和代码测试等重要模块，LLM-Geo已展现出迈向下一代AI驱动GIS的潜在路径。我们呼吁地理信息科学界投入更多精力开展自主式GIS的研究与开发，使空间分析更简易、更快速，并为更广泛用户群体所用。