Large language model-driven GIS analysis: methods, applications, and prospects

doi:10.11947/j.AGCS.2025.20240468

Abstract

Abstract:

The rapid development of large language models (LLMs) provide a new approach for GIS analysis, leading to the large language model-driven GIS analysis technical architecture (LLM4GIS). Based on the latest research up to October 2024, this paper reviews the evolution of GIS analysis and summarizes the LLM4GIS technical architecture from 3 aspects: application modes, datasets and evaluation methods. It also summarizes the research progress of LLM in GIS analysis tasks such as knowledge question-answering, knowledge extraction, spatiotemporal reasoning, and analyzing and modeling. Finally, the paper prospects the future research directions of GIS4LLM in 5 aspects: collaborative understanding of multimodal spatio-temporal data, balancing generalization with depth, enhancing interpretability and credibility, transitioning to embodied intelligence and edge intelligence, and the development of intelligent and universal GIS analysis. This paper provides inspiration for achieving mutual empowerment between LLM4GIS and GIS4LLM.

Key words: large language model, GIS analysis, prompt engineering, retrieval-augmented generation, fine-tuning, agent, LLM4GIS, GIS4LLM

CLC Number:

P282

Huayi WU, Zhangxiao SHEN, Shuyang HOU, Jianyuan LIANG, Anqi ZHAO, Haoyue JIAO, Zhipeng GUI, Xuefeng GUAN. Large language model-driven GIS analysis: methods, applications, and prospects[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(4): 621-635.

Figures/Tables 7

Tab. 1

Fig. 1

Fig. 2

Fig. 3

Tab. 2

Typical large language models for GIS analysis"

模型名称	预训练模型	类别	任务场景	描述
K2^[39]	LLaMA2-7B	1、2	知识问答	利用地球科学领域的专用语料库进行微调，提升了对地球科学知识的理解、推理和应用能力
GeoGalactica^[43]	Galactica-30B	1、2	知识问答	利用GeoSignal-v2数据集构建的地球科学专用大语言模型，提升了在地质学、地球物理、气象学等领域的知识问答、理解与推理能力
BB-GeoGPT^[40]	LLaMA2-7B	1、2	知识问答知识抽取时空推理	通过GIS领域专业语料库微调，优化了基础模型在地理空间知识理解、地理问题问答和空间关系抽取等任务中的性能
ClimateGPT^[32]	LLaMA2-7B、13B、70B	1、2	知识问答时空推理	通过模型微调和检索增强生成，整合自然、经济与社会科学等领域知识，为气候变化研究和决策提供跨学科多语言问答服务
OceanGPT^[44]	MiniCPM-2B、LLaMA2-7B、LLaMA3-8B	1、2	知识问答知识抽取时空推理	面向海洋科学任务，具备指令生成、知识推理和初步的具身智能能力，可支持海洋机器人在海洋工程任务中的规划与操作
GeoCode-GPT^[45]	Code-LLaMA-7B	1、2	分析建模	通过地理空间代码语料库微调，实现多平台多编程语言地理空间代码生成任务，同时建立GeoCode-Eval地理空间代码生成能力评价标准
ChatGeoAI^[46]	LLaMA2	2	分析建模	可通过自然语言查询自动生成并执行PyQGIS脚本，支持非专业用户使用GIS工具
Typhoon-T5^[33]	T5-large	2	知识问答时空推理	整合台风气象知识、灾害案例和灾害管理数据的台风灾害知识问答和预测系统
LLaMA-CoPB^[47]	LLaMA3-8B	2	时空推理	结合“计划行为理论”设计的时空推理模型，可用于移动行为生成
UrbanGPT^[48]	ChatGLM3-6B-Base	2	时空推理	城市动态预测设计专用大模型，能够在零样本场景下捕捉复杂的时空关系，服务于交通流量、人口迁移和犯罪率等预测任务

Tab. 2

Fig. 4

Tab. 3

Typical datasets used in large language models for GIS analysis"

用途	名称	时间	应用场景	获取方式	描述
知识语料库	GeoLLM^[26]	2024-02	时空推理	开源获取	基于OpenStreetMap数据，生成地理坐标与社会经济信息映射提示的地理空间知识，应用于人口密度和经济状况等GIS分析任务
	GeoQAMap^[34]	2023-09	知识问答	开源获取	基于Wikidata知识库中的地理实体及其相关信息，增强地理问题的自动解答和地图可视化的能力
	Geo-FuB^[36]	2024-10	分析建模	规则匹配	基于154 075条Google Earth Engine脚本，通过抽象语法树和Apriori算法提取函数算子组合，并进行语义映射，构建操作-函数知识库
	文献[37]	2023-06	知识问答	开源获取	包含219个实体和236种关系类型的洪水知识图谱，以及定义操作关系和输入输出数据结构的GIS知识图谱
预训练集	BB-GeoPT^[40]	2024-06	分析建模	开源获取	包含2499篇GIS论文和24 408条Wikipedia页面，涵盖GIS领域的理论和操作内容
	GeoCode-PT^[45]	2024-10	分析建模	开源获取	包含275 374段代码、10 190个操作符、853个数据集知识条目，涉及多语言地理代码示例和操作说明，用于提升地理空间代码生成能力
	GeoCorpus^[43]	2024-01	知识问答	开源获取	包含5 980 293篇地球科学相关论文，旨在提高模型在地球科学任务中的理解和生成能力
	TransGPT-PT^[54]	2024-02	时空推理	开源获取	包含9760万词元和超过3000张图像的交通领域文献和报告，用于提升模型在交通分析与问答任务中的专业能力
指令微调数据集	GeoCode-SFT^[45]	2024-10	分析建模	大语言模型合成	使用结构化遍历算法和Self-instruct框架，生成502 047条指令数据，涵盖运算符、数据集、平台语言理解和代码总结，用于增强模型的地理空间代码生成能力
	ClimateIQA^[74]	2024-06	知识问答	规则匹配	包含8760张气象热图和254 040个问答对，旨在训练视觉-语言模型识别极端天气事件，并准确解释气象热图
	MMRS-1M^[68]	2024-01	时空推理	专家经验标注	整合了34个现有遥感数据集及百万级图文数据对，旨在提升模型在遥感任务上的通用性与推理能力
	CityInstruction^[81]	2024-06	时空推理	开源获取	包含34万条通用指令数据和25万条城市领域数据，涵盖实体认知、空间探索、空间推理，旨在提升大语言模型的城市空间认知与任务解决能力
评估集	OceanBench^[44]	2024-10	知识问答	规则匹配	包含15个海洋相关任务，涵盖问答、分类、生成和推理等多种任务类型，旨在评估大语言模型在海洋科学任务上的执行能力
	PPNL^[71]	2024-10	时空推理	规则匹配	包含64 080个单目标和123 600个多目标路径规划任务实例，旨在评估大语言模型的时空推理与规划能力
	GeoCode-Bench^[77]	2024-10	分析建模	大语言模型合成	包含5000道选择题、1500道填空题、1500道判断题及1000道主观编程任务，旨在评估大语言模型生成地理空间代码的能力
	VRSBench^[78]	2024-06	时空推理	专家经验标注	包含29 614张遥感影像、52 472个目标描述句、123 221个问答对和详细图像描述，旨在评估和提升视觉-语言模型在遥感影像理解任务上的性能
工具集	LLM-Find^[30]	2024-08	知识抽取	专家经验标注	支持6种数据源，提供元数据及技术支持，旨在通过自然语言指令实现地理数据的自动检索、下载和分析
	ShapefileGPT^[54]	2024-10	分析建模	专家经验标注	专门用于Shapefile处理的27个功能库，涵盖几何操作、空间查询和拓扑分析等任务
	POIGPT^[82]	2024-06	知识抽取	开源获取	通过集成命名实体识别模块与Google Map API调用工具，识别并定位社交媒体文本中的兴趣点
	MapGPT^[83]	2024-10	分析建模	开源获取	包含68种专业制图工具，支持通过自然语言交互生成和优化地图

Tab. 3

References 105

[1]	吴信才. 地理信息系统的基本技术与发展动态[J]. 地球科学, 1998, 23(4): 329-333.
	WU Xincai. Basic technology and development of geographic information system[J]. Earth Science, 1998, 23(4): 329-333.
[2]	李德仁. 论21世纪遥感与GIS的发展[J]. 武汉大学学报(信息科学版), 2003, 28(2): 127-131.
	LI Deren. Towards the development of remote sensing and GIS in the 21st century[J]. Geomatics and Information Science of Wuhan University, 2003, 28(2): 127-131.
[3]	闾国年, 袁林旺, 陈旻, 等. 地理信息学科发展的思考[J]. 地球信息科学学报, 2024, 26(4): 767-778.
	LÜ Guonian, YUAN Linwang, CHEN Min, et al. Reflections on the development of the geographic information discipline[J]. Journal of Geo-Information Science, 2024, 26(4): 767-778.
[4]	苏世亮, 王卓伦, 何深静, 等. 社会地理计算的理论逻辑与研究范式及展望[J]. 地理学报, 2024, 79(1): 187-205.
	SU Shiliang, WANG Zhuolun, HE Shenjing, et al. Rethinking the theoretical genesis, research paradigm and research agenda of Geo-computational Social Sciences[J]. Acta Geographica Sinica, 2024, 79(1): 187-205.
[5]	杜清运, 王涛, 任福. 试论地理信息科学的基础学科范式[J]. 武汉大学学报(信息科学版), 2022, 47(12): 2003-2006, 2037.
	DU Qingyun, WANG Tao, REN Fu. On the basic discipline paradigm of geographic information science[J]. Geomatics and Information Science of Wuhan University, 2022, 47(12): 2003-2006, 2037.
[6]	华一新, 赵鑫科, 张江水. 地理信息系统研究新范式[J]. 地球信息科学学报, 2023, 25(1): 15-24.
	HUA Yixin, ZHAO Xinke, ZHANG Jiangshui. New paradigm of geographic information systems research[J]. Journal of Geo-Information Science, 2023, 25(1): 15-24.
[7]	李新, 郑东海, 冯敏, 等. 信息地理学：信息革命重塑地理学[J]. 中国科学：地球科学, 2022, 52(2): 370-373.
	LI Xin, ZHENG Donghai, FENG Min, et al. Information geography: the information revolution reshapes geography[J]. Science China Earth Sciences, 2022, 65(2): 379-382.
[8]	傅伯杰. 地理学：从知识、科学到决策[J]. 地理学报, 2017, 72(11): 1923-1932.
	FU Bojie. Geography: from knowledge, science to decision making support[J]. Acta Geographica Sinica, 2017, 72(11): 1923-1932.
[9]	TEAM G, ANIL R, BORGEAUD S, et al. Gemini: a family of highly capable multimodal models[EB/OL]. [2023-11-01]. https://arxiv.org/abs/2312.11805v4.
[10]	TOUVRON H, LAVRIL T, IZACARD G, et al. LLaMA: open and efficient foundation language models[EB/OL]. [2023-03-01]. https://arxiv.org/abs/2302.13971v1.
[11]	BAI Jinze, BAI Shuai, CHU Yunfei, et al. Qwen technical report[EB/OL]. [2023-03-11]. https://arxiv.org/abs/2309.16609v1.
[12]	SUN Yu, WANG Shuohuan, LI Yukun, et al. ERNIE 2.0: a continual pre-training framework for language understanding[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5): 8968-8975.
[13]	WANG Hanchen, FU Tianfan, DU Yuanqi, et al. Scientific discovery in the age of artificial intelligence[J]. Nature, 2023, 620(7972): 47-60.
[14]	李宇航, 徐志伟, 刘燕华, 等. 人工智能时代的地理科学前沿问题探析[J]. 地理学报, 2024, 79(10): 2409-2424.
	LI Yuhang, XU Zhiwei, LIU Yanhua, et al. AI for geographical sciences: the frontiers[J]. Acta Geographica Sinica, 2024, 79(10): 2409-2424.
[15]	LI Xin, GUO Yanlong. Paradigm shifts from data-intensive science to robot scientists[J]. Science Bulletin, 2025, 70(1): 14-18.
[16]	王密, 程昫, 潘俊, 等. 大模型赋能智能摄影测量：现状、挑战与前景[J]. 测绘学报, 2024, 53(10): 1955-1966. DOI:. doi: 10.11947/j.AGCS.2024.20240068
	WANG Mi, CHENG Xu, PAN Jun, et al. Large models enabling intelligent photogrammetry: status, challenges and prospects[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(10): 1955-1966. DOI:. doi: 10.11947/j.AGCS.2024.20240068
[17]	燕琴, 顾海燕, 杨懿, 等, 智能遥感大模型研究进展与发展方向[J]. 测绘学报, 2024, 53(10): 1967-1980. DOI:. doi: 10.11947/j.AGCS.2024.20240053
	YAN Qin, GU Haiyan, YANG Yi, et al, Research progress and trend of intelligent remote sensing large model[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(10): 1967-1980. DOI:. doi: 10.11947/j.AGCS.2024.20240053
[18]	张良培, 张乐飞, 袁强强. 遥感大模型：进展与前瞻[J]. 武汉大学学报(信息科学版), 2023, 48(10): 1574-1581.
	ZHANG Liangpei, ZHANG Lefei, YUAN Qiangqiang. Large remote sensing model: progress and prospects[J]. Geomatics and Information Science of Wuhan University, 2023, 48(10): 1574-1581.
[19]	杨必胜, 陈一平, 邹勤. 从大模型看测绘时空信息智能处理的机遇和挑战[J]. 武汉大学学报(信息科学版), 2023, 48(11): 1756-1768.
	YANG Bisheng, CHEN Yiping, ZOU Qin. Opportunities and challenges of spatiotemporal information intelligent processing of surveying and mapping in the era of large models[J]. Geomatics and Information Science of Wuhan University, 2023, 48(11): 1756-1768.
[20]	CHEN Min, QIAN Zhen, BOERS N, et al. Collaboration between artificial intelligence and Earth science communities for mutual benefit[J]. Nature Geoscience, 2024, 17(10): 949-952.
[21]	ZHAO Tianjie, WANG Sheng, OUYANG Chaojun, et al. Artificial intelligence for geoscience: progress, challenges, and perspectives[J]. The Innovation, 2024, 5(5): 100691.
[22]	ZHOU Chunting, LIU Pengfei, XU Puxin, et al. LIMA: less is more for alignment[EB/OL]. [2023-10-10]. https://arxiv.org/abs/2305.11206v1.
[23]	ZHANG Yifan, WEI Cheng, HE Zhengting, et al. GeoGPT: an assistant for understanding and processing geospatial tasks[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 131: 103976.
[24]	ROBERTS J, LÜDDECKE T, DAS S, et al. GPT4GEO: how a language model sees the world's geography[EB/OL]. [2023-12-10]. https://arxiv.org/abs/2306.00020v1.
[25]	MAI Gengchen, CUNDY C, CHOI K, et al. Towards a foundation model for geospatial artificial intelligence[C]//Proceedings of the 30th International Conference on Advances in Geographic Information Systems. Seattle: ACM Press, 2022: 1-4.
[26]	MANVI R, KHANNA S, MAI Gengchen, et al. GeoLLM: extracting geospatial knowledge from large language models[EB/OL]. [2023-06-12]. https://arxiv.org/abs/2310.06213v2.
[27]	ZHANG Zheng, AMIRI H, LIU Zhenke, et al. Large language models for spatial trajectory patterns mining[EB/OL]. [2023-06-10]. https://arxiv.org/abs/2310.04942v1.
[28]	BENEDUCE C, LEPRI B, LUCA M. Large language models are zero-shot next location predictors[EB/OL]. [2024-10-10]. https://arxiv.org/abs/2405.20962v3.
[29]	FENG Shanshan, LYU Haoming, LI Fan, et al. Where to move next: zero-shot generalization of LLMs for next POI recommendation[C]//Proceedings of 2024 IEEE Conference on Artificial Intelligence. Singapore: IEEE, 2024: 1530-1535.
[30]	NING Huan, LI Zhenlong, AKINBOYEWA T, et al. An autonomous GIS agent framework for geospatial data retrieval[EB/OL]. [2024-12-10]. https://arxiv.org/abs/2407.21024v2.
[31]	GAO Yunfan, XIONG Yun, GAO Xinyu, et al. Retrieval-augmented generation for large language models: a survey[EB/OL]. [2023-11-11]. https://arxiv.org/abs/2312.10997v5.
[32]	THULKE D, GAO Yingbo, PELSER P, et al. ClimateGPT: towards AI synthesizing interdisciplinary research on climate change[EB/OL]. [2024-02-10]. https://arxiv.org/abs/2401.09646v1.
[33]	XIA Yongqi, HUANG Yi, QIU Qianqian, et al. A question and answering service of typhoon disasters based on the T5 large language model[J]. ISPRS International Journal of Geo-Information, 2024, 13(5): 165.
[34]	FENG Yu, DING Linfang, XIAO Guohui. GeoQAMap-geographic question answering with maps leveraging llm and open knowledge base[C]//Proceedings of the 12th International Conference on Geographic Information Science. [S.l.]: IEEE, 2023: 1-7.
[35]	SHEKHAR S, PAPALEXAKIS V, GAO J, et al. Geospatial topological relation extraction from text with knowledge augmentation[C]//Proceedings of 2024 SIAM International Conference on Data Mining. Philadelphia: Society for Industrial and Applied Mathematics, 2024.
[36]	HOU Shuyang, ZHAO Anqi, LIANG Jianyuan, et al. Geo-Fub: a method for constructing an operator-function knowledge base for geospatial code generation tasks using large language models[EB/OL]. [2024-10-30]. https://www.ssrn.com/abstract=4951342. DOI:. doi: 10.2139/ssrn.4951342
[37]	ZHU Jun, DANG Pei, CAO Yungang, et al. A flood knowledge-constrained large language model interactable with GIS: enhancing public risk perception of floods[J]. International Journal of Geographical Information Science, 2024, 38(4): 603-625.
[38]	吴华意, 赵安琪, 梁健源, 等. 面向地学分析AI建模的地理信息服务层次网络模型[J]. 测绘学报, 2024, 53(11): 2053-2063. DOI:. doi: 10.11947/j.AGCS.2024.20240109
	WU Huayi, ZHAO Anqi, LIANG Jianyuan, et al. Five-layer hierarchical network (5-HiNet) of geospatial information service for AIGC of geographic analysis model[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(11): 2053-2063. DOI:. doi: 10.11947/j.AGCS.2024.20240109
[39]	DENG Cheng, ZHANG Tianhang, HE Zhongmou, et al. K2: a foundation language model for geoscience knowledge understanding and utilization[C]//Proceedings of the 17th ACM International Conference on Web Search and Data Mining. Merida: ACM Press, 2024: 161-170.
[40]	ZHANG Yifan, WANG Zhiyun, HE Zhengting, et al. BB-GeoGPT: a framework for learning a large language model for geographic information science[J]. Information Processing & Management, 2024, 61(5): 103808.
[41]	GLM T, ZENG Aohan. ChatGLM: a family of large language models from GLM-130B to GLM-4 all tools[EB/OL]. [2023-10-15]. https://arxiv.org/abs/2406.12793v2.
[42]	TAYLOR R, KARDAS M, CUCURULL G, et al. Galactica: a large language model for science[EB/OL]. [2023-11-05]. https://arxiv.org/abs/2211.09085v1.
[43]	LIN Zhouhan, DENG Cheng, ZHOU Le, et al. GeoGalactica: a scientific large language model in geoscience[EB/OL]. [2023-12-10]. https://arxiv.org/abs/2401.00434v2.
[44]	BI Zhen, ZHANG Ningyu, XUE Yida, et al. OceanGPT: a large language model for ocean science tasks[EB/OL]. [2023-10-11]. https://arxiv.org/abs/2310.02031v8.
[45]	HOU Shuyang, SHEN Zhangxiao, ZHAO Anqi, et al. GeoCode-GPT: a large language model for geospatial code generation[J]. International Journal of Applied Earth Observation and Geoinformation, 2025, 138: 104456.
[46]	MANSOURIAN A, OUCHEIKH R. ChatGeoAI: enabling geospatial analysis for public through natural language, with large language models[J]. ISPRS International Journal of Geo-Information, 2024, 13(10): 348.
[47]	SHAO Chenyang, XU Fengli, FAN Bingbing, et al. Chain-of-planned-behaviour workflow elicits few-shot mobility generation in LLMs[EB/OL]. [2024-11-01]. https://arxiv.org/abs/2402.09836v2.
[48]	LI Zhonghang, XIA Lianghao, TANG Jiabin, et al. UrbanGPT: spatio-temporal large language models[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Barcelona: ACM Press, 2024: 5351-5362.
[49]	WANG Lei, MA Chen, FENG Xueyang, et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science, 2024, 18(6): 186345.
[50]	LI Zhenlong, NING Huan. Autonomous GIS: the next-generation AI-powered GIS[J]. International Journal of Digital Earth, 2023, 16(2): 4668-4686.
[51]	冯丽妃. 十问“坤元”大模型[N]. 中国科学报, 2024-09-20: 001.
	FENG Lifei. Ten questions about sigma geography[N]. China Science Daily, 2024-09-20: 001.
[52]	SCHUMANN R, ZHU Wanrong, FENG Weixi, et al. VELMA: verbalization embodiment of LLM agents for vision and language navigation in street view[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(17): 18924-18933.
[53]	XU Fengli, ZHANG Jun, GAO Chen, et al. Urban generative intelligence (UGI): a foundational platform for agents in embodied city environment[EB/OL]. [2024-11-01]. https://arxiv.org/abs/2312.11813v1.
[54]	LIN Qingming, HU Rui, LI Huaxia, et al. ShapefileGPT: a multi-agent large language model framework for automated shapefile processing[EB/OL]. [2024-10-23]. https://arxiv.org/abs/2410.12376v2.
[55]	ZHOU Zhilun, LIN Yuming, JIN Depeng, et al. Large language model for participatory urban planning[EB/OL]. [2024-10-01]. http://arxiv.org/abs/2402.17161.
[56]	HU Xuke, KERSTEN J, KLAN F, et al. Toponym resolution leveraging lightweight and open-source large language models and geo-knowledge[J]. International Journal of Geographical Information Science, 2024, 4: 1-28.
[57]	LIU Zilong, JANOWICZ K, CURRIER K, et al. Measuring geographic diversity of foundation models with a natural language-based geo-guessing experiment on GPT-4[J]. AGILE: GIScience Series, 2024, 5: 1-7.
[58]	YAN Yibo, LEE J. GeoReasoner: reasoning on geospatially grounded context for natural language understanding[EB/OL]. [2024-11-10]. https://arxiv.org/abs/2408.11366v1.
[59]	LIANG Yuebing, LIU Yichao, WANG Xiaohan, et al. Exploring large language models for human mobility prediction under public events[J]. Computers, Environment and Urban Systems, 2024, 112: 102153.
[60]	XUE Hao, VOUTHAROJA B P, SALIM F D. Leveraging language foundation models for human mobility forecasting[C]//Proceedings of the 30th International Conference on Advances in Geographic Information Systems. Seattle: ACM Press, 2022: 1-9.
[61]	ZHANG Siyao, FU Daocheng, LIANG Wenzhe, et al. TrafficGPT: viewing, processing and interacting with traffic foundation models[J]. Transport Policy, 2024, 150: 95-105.
[62]	LIU Lei, YU Shuo, WANG Runze, et al. How can large language models understand spatial-temporal data?[EB/OL]. [2024-10-01]. https://arxiv.org/abs/2401.14192v2.
[63]	WANG Jiawei, JIANG Renhe, YANG Chuang, et al. Large language models as urban residents: an LLM agent framework for personal mobility generation[EB/OL]. [2024-03-11]. https://arxiv.org/abs/2402.14744v3.
[64]	HU Yingjie, MAI Gengchen, CUNDY C, et al. Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages[J]. International Journal of Geographical Information Science, 2023, 37(11): 2289-2318.
[65]	KUCKREJA K, DANISH M S, NASEER M, et al. GeoChat: grounded large vision-language model for remote sensing[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 27831-27840.
[66]	GUO Haonan, SU Xin, WU Chen, et al. Remote sensing ChatGPT: solving remote sensing tasks with ChatGPT and visual models[C]//Proceedings of 2024 IEEE International Geoscience and Remote Sensing Symposium. Athens: IEEE, 2024: 11474-11478.
[67]	ZHAN Yang, XIONG Zhitong, YUAN Yuan. SkyEyeGPT: unifying remote sensing vision-language tasks via instruction tuning with large language model[EB/OL]. [2024-02-11]. https://arxiv.org/abs/2401.09712v1.
[68]	ZHANG Wei, CAI Miaoxin, ZHANG Tong, et al. EarthGPT: a universal multimodal large language model for multisensor image comprehension in remote sensing domain[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5917820.
[69]	MUHTAR D, LI Zhenshi, GU Feng, et al. LHRS-bot: empowering remote sensing with VGI-enhanced large multimodal language model[EB/OL]. [2024-05-10]. https://arxiv.org/abs/2402.02544v4.
[70]	AKINBOYEWA T, NING Huan, LESSANI M N, et al. Automated floodwater depth estimation using large multimodal model for rapid flood mapping[J]. Computational Urban Science, 2024, 4(1): 12.
[71]	AGHZAL M, PLAKU E, YAO Ziyu. Can large language models be good path planners? A benchmark and investigation on spatial-temporal reasoning[EB/OL]. [2023-08-19]. https://arxiv.org/abs/2310.03249v3.
[72]	ZHU He, ZHANG Wenjia, HUANG Nuoxian, et al. PlanGPT: enhancing urban planning with tailored language model and efficient retrieval[EB/OL]. [2024-02-18]. https://arxiv.org/abs/2402.19273v1.
[73]	HOJATI M, FEICK R. Large language models: testing their capabilities to understand and explain spatial concepts[C]//Proceedings of the 12th International Conference on Geographic Information Science. [S.l.]: IEEE, 2024: 1-9.
[74]	CHEN Jian, ZHOU Peilin, HUA Yining, et al. Vision-language models meet meteorology: developing models for extreme weather events detection with heatmaps[EB/OL]. [2024-07-01]. https://arxiv.org/abs/2406.09838v1.
[75]	NING Yansong, LIU Hao. UrbanKGent: a unified large language model agent framework for urban knowledge graph construction[EB/OL]. [2024-06-05]. https://arxiv.org/abs/2402.06861v2.
[76]	WANG Yizhong, KORDI Y, MISHRA S, et al. Self-instruct: aligning language models with self-generated instructions[EB/OL]. [2023-11-11]. https://arxiv.org/abs/2212.10560v2.
[77]	HOU Shuyang, SHEN Zhangxiao, LIANG Jianyuan, et al. Can large language models generate geospatial code?[EB/OL]. [2024-09-11]. https://arxiv.org/abs/2410.09738v2.
[78]	LI Xiang, DING Jian, ELHOSEINY M. VRSBench: a versatile vision-language benchmark dataset for remote sensing image understanding[EB/OL]. [2024-11-01]. https://arxiv.org/abs/2406.12384v2.
[79]	YUAN Zhenghang, XIONG Zhitong, MOU Lichao, et al. ChatEarthNet: a global-scale image-text dataset empowering vision-language geo-foundation models[J]. Earth System Science Data, 2025, 17(3): 1245-1263.
[80]	SINGH S, FORE M, STAMOULIS D. GeoLLM-engine: a realistic environment for building geospatial copilots[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle: IEEE, 2024: 585-594.
[81]	FENG Jie, DU Yuwei, LIU Tianhui, et al. CityGPT: empowering urban spatial cognition of large language models[EB/OL]. [2024-10-20]. https://arxiv.org/abs/2406.13948v1.
[82]	KIM H, LEE S. POI GPT: extracting POI information from social media text data[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2024, XLVIII-4/W10-2024: 113-118.
[83]	ZHANG Yifan, HE Zhengting, LI Jingxuan, et al. MapGPT: an autonomous framework for mapping by integrating large language model and cartographic tools[J]. Cartography and Geographic Information Science, 2024, 51(6): 717-743.
[84]	LI Wenbin, YAO Di, ZHAO Ruibo, et al. STBench: assessing the ability of large language models in spatio-temporal analysis[EB/OL]. [2024-10-12]. https://arxiv.org/abs/2406.19065v1.
[85]	ROBERTS J, LÜDDECKE T, SHEIKH R, et al. Charting new territories: exploring the geographic and geospatial capabilities of multimodal LLMs[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle: IEEE, 2024: 554-563.
[86]	MOONEY P. Towards understanding the geospatial skills of ChatGPT[C]//Proceedings of the 6th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery. New York: ACM Press, 2023: 85-94.
[87]	XU Liuchang, ZHAO Shuo, LIN Qingming, et al. Evaluating large language models on spatial tasks: a multi-task benchmarking study[EB/OL]. [2024-11-15]. https://arxiv.org/abs/2408.14438v4.
[88]	HOCHMAIR H H, JUHÁSZ L, KEMP T. Correctness comparison of ChatGPT-4, gemini, Claude-3, and copilot for spatial tasks[J]. Transactions in GIS, 2024, 28(7): 2219-2231.
[89]	HAO Yanan, QI Jin, MA Xiaowen, et al. An LLM-based inventory construction framework of urban ground collapse events with spatiotemporal locations[J]. ISPRS International Journal of Geo-Information, 2024, 13(4): 133.
[90]	HE Junlin, NIE Tong, MA Wei. Geolocation representation from large language models are generic enhancers for spatio-temporal learning[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2408.12116v2.
[91]	GUPTA D V, ALI ISHAQUI A S, KADIYALA D K. Geode: a zero-shot geospatial question-answering agent with explicit reasoning and precise spatio-temporal retrieval[EB/OL]. [2024-07-07]. https://arxiv.org/abs/2407.11014v1.
[92]	LAWSON J R, TRUJILLO-FALCÓN J E, SCHULTZ D M, et al. Pixels and predictions: potential of GPT-4V in meteorological imagery analysis and forecast communication[EB/OL]. [2024-05-16]. https://arxiv.org/abs/2404.15166v2.
[93]	WANG Peng, WEI Xiang, HU Fangxu, et al. TransGPT: multi-modal generative pre-trained transformer for transportation[EB/OL]. [2024-07-01]. https://arxiv.org/abs/2402.07233v1.
[94]	GOECKS V G, WAYTOWICH N R. DisasterResponseGPT: large language models for accelerated plan of action development in disaster response scenarios[EB/OL]. [2023-11-11]. https://arxiv.org/abs/2306.17271v1.
[95]	NUNES R O, SPRITZER A S, BALREIRA D G. An evaluation of large language models for geological named entity recognition[EB/OL]. [2024-11-16]. https://www.researchgate.net/profile/Rafael-Nunes-35/publication/383822506_An_Evaluation_of_Large_Language_Models_for_Geological_Named_Entity_Recognition/links/66dcac42f84dd1716cd713c0/An-Evaluation-of-Large-Language-Models-for-Geological-Named-Entity-Recognition.pdf.
[96]	LIANG Jianyuan, ZHAO Anqi, HOU Shuyang, et al. A GPT-enhanced framework on knowledge extraction and reuse for geographic analysis models in Google Earth Engine[J]. International Journal of Digital Earth, 2024, 17(1): 2398063.
[97]	PENG Mingxing, GUO Xusen, CHEN Xianda, et al. LC-LLM: explainable lane-change intention and trajectory predictions with large language models[EB/OL]. [2024-10-30]. https://arxiv.org/abs/2403.18344v2.
[98]	JIANG Yue, CHAO Qin, CHEN Yile, et al. UrbanLLM: autonomous urban activity planning and management with large language models[EB/OL]. [2024-10-30]. https://arxiv.org/abs/2406.12360v1.
[99]	WANG Xinglei, FANG Meng, ZENG Zichao, et al. Wherewould I go next? Large language models as human mobility predictors[EB/OL]. [2023-11-03]. https://arxiv.org/abs/2308.15197v2.
[100]	ZENG Qingbin, YANG Qinglong, DONG Shunan, et al. Perceive, reflect, and plan: designing LLM agent for goal-directed city navigation without instructions[EB/OL]. [2024-11-01]. https://arxiv.org/abs/2408.04168v3.
[101]	CHEN Jiaqi, LIN Bingqian, XU Ran, et al. MapGPT: map-guided prompting with adaptive path planning for vision-and-language navigation[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok: ACL, 2024: 9796-9810.
[102]	BALSEBRE P, HUANG Weiming, CONG Gao. LAMP: a language model on the map[EB/OL]. [2024-11-10]. https://arxiv.org/abs/2403.09059v2.
[103]	MAI Gengchen, HUANG Weiming, SUN Jin, et al. On the opportunities and challenges of foundation models for geospatial artificial intelligence[EB/OL]. [2023-11-16]. https://arxiv.org/abs/2304.06798v1.
[104]	YAMADA Y, BAO Yihan, LAMPINEN A K, et al. Evaluating spatial understanding of large language models[EB/OL]. [2023-11-11]. https://arxiv.org/abs/2310.14540v3.
[105]	GRAMACKI P, MARTINS B, SZYMASKI P. Evaluation of code LLMs on geospatial code generation[EB/OL]. [2024-11-15]. https://arxiv.org/abs/2410.04617v2.

GIS分析发展阶段	经验科学	数学机理	计算模拟	数据驱动	AI驱动
分析特征	纸质地图量测	计量地理学分析	基于工具的空间建模分析	时空大数据挖掘与预测分析	智能推理与自动化分析
数据特征	少量、单一观测数据	结构化数据	非结构化数据	异构数据	多模态数据
需求特征	定性	定量	定位、拓扑	复杂地理过程建模	动态决策与实时适配
模型特征	—	统计模型	空间分析模型	基于数据训练模型	生成式大模型
典型方法	实地观测与人工分析	空间插值、空间聚类	缓冲区分析、叠置分析	深度学习、机器学习	提示工程、检索增强生成、模型微调、智能体
典型案例	传染病疫情分布推断	人口密度趋势、生态区划	洪水淹没、设施选址	交通预测、城市功能区识别	知识问答、知识抽取、时空推理、分析建模