Open-source GIS LLM Copilot: towards an autonomous GIS agent for spatial analysis. Enabling non-experts to perform geospatial analysis with minimal prior knowledge. Also offering a true open-source framework based on QGIS to potentially keep data local to you.
Interesting paper from Akinboyewa et al (2025). Links to the paper and code in GitHub in the comments.
This can be a fairer and more equitable alternative to uploading your data to web hosted online platforms, where you give the proprietor rights to your data in exchange for using their functionality.
Abstract
Recent advancements in generative artificial intelligence (AI), particularly Large Language Models (LLMs), offer promising capabilities for spatial analysis. However, their integration with established GIS platforms remains underexplored. In this study, we propose a framework that embeds LLMs into existing GIS platforms, using QGIS as a case study. Our approach leverages LLMs’ reasoning and coding abilities to autonomously generate spatial analysis workflows through an informed agent equipped with comprehensive documentation of key GIS tools and parameters. External tools such as GeoPandas are also incorporated to enhance the system’s geoprocessing capabilities. Based on this framework, we developed a ‘GIS Copilot’ that enables users to interact with QGIS using natural language. We evaluated the copilot across over 100 tasks of varying complexity including basic (single tool/layer), intermediate (multistep with guidance), and advanced (multistep without guidance). Results show high success rates for basic and intermediate tasks, with challenges remaining in fully autonomous execution of advanced tasks. The GIS Copilot advances the vision of autonomous GIS by enabling non-experts to perform geospatial analysis with minimal prior knowledge. While full autonomy is not yet achieved, the copilot demonstrates significant potential for simplifying GIS workflows and enhancing decision-making processes.
“Unlike traditional black-box models, the Copilot clearly presents each stage of the process, including tool selection and code generation, with generated code displayed in real time. Additionally, the generated code can be further edited and executed manually as needed. This approach allows users to inspect and understand each action taken by the Copilot, so that they can trace how results are achieved. Users are encouraged to review the generated code and results actively, rather than relying on them blindly. This approach highlights the collaborative nature of a ‘copilot’ system that supports rather than replaces expert decision-making in GIS.”
https://www.tandfonline.com/doi/full/10.1080/17538947.2025.2497489#abstract
GitHub: https://github.com/Teakinboyewa/SpatialAnalysisAgent
