[论文解读] GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT

Yifan Zhang, Wei Cheng+3 more|arXiv (Cornell University)|Jul 16, 2023

Natural Language Processing Techniques被引用 17

一句话总结

GeoGPT 将基于语言模型的自治代理与 GIS 工具池结合起来，以自然语言理解用户需求，并自动规划、执行，输出地理空间结果。

ABSTRACT

Decision-makers in GIS need to combine a series of spatial algorithms and operations to solve geospatial tasks. For example, in the task of facility siting, the Buffer tool is usually first used to locate areas close or away from some specific entities; then, the Intersect or Erase tool is used to select candidate areas satisfied multiple requirements. Though professionals can easily understand and solve these geospatial tasks by sequentially utilizing relevant tools, it is difficult for non-professionals to handle these problems. Recently, Generative Pre-trained Transformer (e.g., ChatGPT) presents 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 lower the threshold of non-professional users to solve geospatial 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 with the instruction of only natural language. In other words, GeoGPT is used to understand the demands of non-professional users merely based on input natural language descriptions, and then think, plan, and execute defined GIS tools to output final effective results. 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.

研究动机与目标

• 降低非专业用户解决地理空间任务的门槛。
• 将语言模型的大规模语义理解与成熟的 GIS 工具桥接，以自动化 GIS 工作流。
• 实现由自然语言驱动的自主数据采集、处理、分析与制图。

提出的方法

• 将 LLM（GPT-3.5-turbo）用作决策者，以理解用户需求并规划工具使用。
• 构建包含数据采集、处理/分析和可视化工具的 GIS 工具池。
• 利用 LangChain 将 LLM 与外部 GIS 工具连接，并执行引导工具使用的提示协议。
• 应用顺序的、逐步的推理与行动循环（think–act–observe）来解决任务。
• 通过案例研究（数据爬取、设施选址、空间查询和制图）来验证自治性和适应性。

实验结果

研究问题

• RQ1 自然语言输入是否能够被准确解读以选择并对地理信息系统工具进行排序？
• RQ2 在数据收集、分析和制图等常见任务上，自治的基于 GPT 的代理在多大程度上能够复现专业 GIS 工作流程？
• RQ3 使用基于 LLM 的 GIS 代理时的局限性与不确定性有哪些，以及如何缓解？

主要发现

• GeoGPT 可以从自然语言提示中自主规划并执行顺序 GIS 操作，以完成地理空间任务。
• 该框架通过可重用的工具池支持数据爬取、空间查询、设施选址和专题制图。
• 案例研究验证了加载数据集、应用缓冲/相交/擦除等操作，以及输出裁剪栅格、矢量地图和最终结果等能力。
• 讨论了与 LLM 的不确定性和工具名称对齐问题，并提出保护机制以减少不匹配。