在新兴大语言模型(LLMs)的推动下,自主地理信息系统(GIS)智能体有潜力完成空间分析和制图任务。然而,在支持完全自主的GIS智能体方面仍存在研究空白:如何使智能体能够发现并下载地理空间分析所需的数据。本研究提出了一种自主GIS智能体框架,该框架能够通过生成、执行和调试程序来检索所需的地理空间数据。该框架利用LLM作为决策者,从预定义的数据源列表中选择合适的数据源,并从所选数据源获取数据。每个数据源都配有一本手册,记录数据检索所需的元数据和技术细节。所提出的框架采用即插即用风格设计,以确保灵活性和可扩展性。人类用户或自主数据抓取器可以通过添加新手册来增加新的数据源。我们基于该框架开发了一个原型智能体,以QGIS插件(GeoData Retrieve Agent)和Python程序的形式发布。实验结果表明,该智能体能够从多种数据源检索数据,包括OpenStreetMap、美国人口普查局的行政边界和人口统计数据、ESRI World Imagery的卫星底图、OpenTopography.org的全球数字高程模型(DEM)、商业提供商的气象数据以及NYTimes GitHub上的COVID-19病例数据。本研究是开发自主地理空间数据检索智能体的首批尝试之一。
英文摘要:
Powered by the emerging large language models (LLMs), autonomous geographic information systems (GIS) agents have the potential to accomplish spatial analyses and cartographic tasks. However, a research gap exists to support fully autonomous GIS agents: how to enable agents to discover and download the necessary data for geospatial analyses. This study proposes an autonomous GIS agent framework capable of retrieving required geospatial data by generating, executing, and debugging programs. The framework utilizes the LLM as the decision-maker, selects the appropriate data source (s) from a pre-defined source list, and fetches the data from the chosen source. Each data source has a handbook that records the metadata and technical details for data retrieval. The proposed framework is designed in a plug-and-play style to ensure flexibility and extensibility. Human users or autonomous data scrawlers can add new data sources by adding new handbooks. We developed a prototype agent based on the framework, released as a QGIS plugin (GeoData Retrieve Agent) and a Python program. Experiment results demonstrate its capability of retrieving data from various sources including OpenStreetMap, administrative boundaries and demographic data from the US Census Bureau, satellite basemaps from ESRI World Imagery, global digital elevation model (DEM) from OpenTopography.org, weather data from a commercial provider, the COVID-19 cases from the NYTimes GitHub. Our study is among the first attempts to develop an autonomous geospatial data retrieval agent.
GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT
School of Geography and Information Engineering, China University of Geosciences(中国地质大学地理与信息工程学院);National Engineering Research Center for Geographic Information System, China University of Geosciences(中国地质大学地理信息系统国家工程研究中心)
GIScience in the Era of Artificial Intelligence: A Research Agenda Towards Autonomous GIS
The Pennsylvania State University(宾夕法尼亚州立大学);University of Wisconsin – Madison(威斯康星大学麦迪逊分校);University of Vienna(维也纳大学);Arizona State University(亚利桑那州立大学);U.S. Geological Survey(美国地质调查局);George Mason University(乔治梅森大学);Oak Ridge National Laboratory (ORNL)(橡树岭国家实验室);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Auckland(奥克兰大学);University of Minnesota(明尼苏达大学);Texas A&M University(德克萨斯农工大学);McGill University(麦吉尔大学);University of South Carolina(南卡罗来纳大学)
GeoContra: From Fluent GIS Code to Verifiable Spatial Analysis with Geography-Grounded Repair
School of Big Data and Artificial Intelligence, Guangdong University of Finance and Economics(大数据与人工智能学院,广东财经大学);School of Geography and Environment Economics, Guangdong University of Finance & Economics(地理与环境经济学院,广东财经大学);Guangdong Engineering Research Center of Low-Altitude Remote Sensing Intelligent Monitoring(低空遥感智能监测工程研究中心)
Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation
Dept. of Systems Design Engineering, University of Waterloo(滑铁卢大学系统设计工程系);SkyWatch;Dept. of Geography and Environmental Management, University of Waterloo(滑铁卢大学地理与环境管理系);Dept. of Geomatics Engineering, University of Calgary(卡尔加里大学测绘工程系)
Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization
Department of Systems Design Engineering, University of Waterloo(系统设计工程系,滑铁卢大学);Department of Mechatronics Engineering, University of Waterloo(机电工程系,滑铁卢大学);Department of Geomatics Engineering, University of Calgary(测绘工程系,卡尔加里大学);Department of Geography and Environmental Management, University of Waterloo(地理与环境管理系,滑铁卢大学)
GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models
Universidad Católica de Ávila (UCAV)(阿维拉天主教大学);Johns Hopkins University(约翰霍普金斯大学);Independent Researcher(独立研究者);Center for Geographic Analysis, Harvard University(哈佛大学地理分析中心)
GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
School of Geosciences and Info-Physics, Central South University(中南大学地球科学与信息物理学院);School of Earth Sciences and Spatial Information Engineering, Hunan University of Science and Technology(湖南科技大学地球科学与空间信息工程学院)
A Multimodal Conversational Assistant for the Characterization of Agricultural Plots from Geospatial Open Data
Dept. AI \& Data Analytics CTIC Technology Center Gijón, Spain;Dept. IT CTIC Technology Center Gijón, Spain;Eng. University of Oviedo Gijón, Spain;Dept. R \& D CTIC Technology Center Gijón, Spain
ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing
School of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University(浙江农林大学数学与计算机科学学院);School of Earth Sciences, Zhejiang University(浙江大学地球科学学院);Xiaohongshu(小红书);Baichuan Inc.(百川智能)
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches
School of Computer Science and Engineering, Northeastern University, China(东北大学计算机科学与工程学院);Department of Computer Science and Technology, Institute for AI, Tsinghua University, China(清华大学计算机科学与技术系,人工智能研究院);School of Intelligent Science and Technology, Nanjing University, China(南京大学智能科学与技术学院)
Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations
GeoDS Lab, Department of Geography, University of Wisconsin-Madison, USA(威斯康星大学麦迪逊分校地理系GeoDS实验室);Department of Geography and Regional Research, University of Vienna, Austria(维也纳大学地理与区域研究系);Department of Geography, University of California-Santa Barbara, USA(加州大学圣塔芭芭拉分校地理系)
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学深圳校区);Peng Cheng Laboratory(鹏城实验室)
From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework
MapQaTor: An Extensible Framework for Efficient Annotation of Map-Based QA Datasets
Department of Computer Science and Engineering(计算机科学与工程系);Bangladesh University of Engineering and Technology (BUET)(孟加拉工程与技术大学);Faculty of Information Technology(信息技术学院);Monash University(墨尔本大学);Qatar Computing Research Institute (QCRI)(卡塔尔计算研究中心)
AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice
North Carolina A\&T State University(北卡罗来纳A&T州立大学);The University of Alabama(阿拉巴马大学);North Carolina Agricultural and Technical State University(北卡罗来纳农业与技术州立大学);Amazon AWS(亚马逊AWS)
A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning
National University of Singapore(新加坡国立大学);College of Geodesy and Geomatics, Shandong University of Science and Technology(山东科技大学测绘与空间信息学院);University of the Bundeswehr Munich(慕尼黑联邦国防军大学);Wuhan University(武汉大学);University of Florida(佛罗里达大学);Institute of Remote Sensing and GIS, Peking University(北京大学遥感与地理信息系统研究所);Department of Architecture, National University of Singapore(新加坡国立大学建筑系);Department of Real Estate, National University of Singapore(新加坡国立大学房地产系)
Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events
Arizona State University(亚利桑那州立大学);Alaska Native Tribal Health Consortium(阿拉斯加原住民部落健康联盟);Bentley University(本特利大学);Woodwell Climate Research Center(伍德韦尔气候研究中心)
OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models
The Hong Kong Polytechnic University(香港理工大学);WeBank;Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);The Hong Kong University of Science and Technology(香港科技大学)