Zhenlong Li | May 27, 2024
Call for papers for Special Issue on
Harnessing the Power of Generative AI in GIScience through Autonomous Spatial Agents
in the International Journal of Digital Earth
Guest Editors:
Dr. Zhenlong Li, The Pennsylvania State University, USA. zhenlong@psu.edu
Dr. Song Gao, University of Wisconsin–Madison, USA. song.gao@wisc.edu
Dr. Wenwen Li, Arizona State University, USA. wenwen@asu.edu
Dr. Krzysztof Janowicz, University of Vienna, Austria. krzysztof.janowicz@univie.ac.at
Submission deadline: December 31, 2025
We are pleased to introduce a new Special Issue titled “Harnessing the Power of Generative AI in GIScience through Autonomous Spatial Agents” in the International Journal of Digital Earth (Taylor & Francis, 2022 Impact Factor: 5.1).
Aims and Scope
Over the last decade, GIScience has witnessed significant transformations with the advent of deep learning and artificial intelligence (AI). The rapid development in AI prompted a moonshot by Janowicz et al. (2020) ‘Can we develop an artificial GIS analyst that passes a domain-specific Turing Test by 2030?’. The recent advancements in large generative AI (GenAI) models across language, audio, vision, and multi-modal (such as ChatGPT), as well as research towards potential artificial general intelligence have brought exciting opportunities to realize this moonshot by revolutionizing GIS, spatial analysis, spatial information extraction, knowledge discovery, and ultimately decision-making through autonomous agents (Li and Ning, 2023).
Autonomous agents are computer systems capable of performing tasks and making decisions with minimal or no human intervention. By leveraging GenAI as the reasoning core, autonomous agents in GIScience (or Autonomous Spatial Agents [ASA]) can assist in and automate various spatial tasks such as collecting spatial data, performing spatial analysis, enabling predictive modeling, extracting meaningful insights, creating maps, generating reports, evaluating the results, and making recommendations. Despite the immense potential, research and development of autonomous agents (and AI assistants) in GIScience is still in their early stages and the roadmaps for successful integration are still being charted. Challenges related to methods, techniques, accuracy, biases, ethics, reliability, scalability, explainability, and trustworthiness are paramount. The broader implications of this convergence on mapping, urban planning, environmental studies, disaster management, education, and governance are yet to be explored.
This special issue aims to call for and gather pioneering research at the crossroads of GenAI and GIScience through the exploration, development, and evaluation of autonomous spatial agents (ASA), providing insights to guide future research agendas such as the development of the next-generation AI-powered Autonomous GIS. Potential topics include, but are not limited to, the following:
- Developing spatial data collection agents: using GenAI to assist in discovering, filtering, and accessing existing spatial datasets from vast online geospatial data warehouses and catalogs.
- Developing spatial analysis agents: leveraging GenAI to perform spatial analysis, such as using GenAI as the reasoning core to convert the spatial problems described in natural language to structured solutions such as geoprocessing workflows and structured query language (SQL).
- Developing information extraction agents: using GenAI to extract semantic information from various spatial data, such as flood depth in the photo, wheelchair passibility in street view images, topics and attitudes in news reports across place, languages, and cultural, and geographic fact-check across multi-sources.
- Developing geovisualization and cartography agents: using GenAI to visualize spatial data and relationships, and customize cartographic designs to specific user needs and contexts.
- Examining the ethical and social implications of GenAI and autonomous agents in GIScience, including issues of sustainability, data privacy, security, and the potential for bias in automated spatial analysis.
- Exploring the possibility of research agents tailed for GIScience, such as invoking research questions, planning implementation, assessing results, cutting failed attempts, improving plans, and ultimately advancing our knowledge.
- Investigating the development of interoperability standards for autonomous spatial agents to ensure seamless integration with existing GIS infrastructures and workflows.
- Investigating geographic knowledge graphs as providers or retrieval augmented generation (RAG) for GenAI.
- Benchmarking autonomous spatial agents: Creating benchmark datasets, ranking performance and efficiency of autonomous agents, guiding the selection of various commercial and open-sourced GenAI models (e.g., OpenAI ChatGPT vs Meta Llama 3) in solving spatial problems.
- Explainability and uncertainty of GenAI in GIScience: Investigating explainable GenAI in the GIScience context, quantifying the uncertainties of autonomous processes and results.
- Investigating and discussing the disruptive and supportive effects of GenAI in GIScience education.
- Examining the role of human expertise in guiding, training, and refining autonomous spatial agents to enhance their performance and reliability in GIScience tasks (Human-AI collaboration).
References
- Janowicz, K., Gao, S., McKenzie, G., Hu, Y., Bhaduri, B. (2020). GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond. International Journal of Geographical Information Science, 34(4), 625-636. https://doi.org/10.1080/13658816.2019.1684500
- Li, Z. and Ning, H. (2023). Autonomous GIS: the next-generation AI-powered GIS, International Journal of Digital Earth. https://doi.org/10.1080/17538947.2023.2278895
- Wang S., Hu T., Huang X., Li Y., Zhang C., Ning H., Zhu R., Li Z., Ye X. (2024). GPT, large language models (LLMs) and generative artificial intelligence (GAI) models in geospatial science: a systematic review. International Journal of Digital Earth. https://doi.org/10.1080/17538947.2024.2353122
