EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative AI for Geospatial Analysis: Fine-Tuning ChatGPT to Convert Natural Language into Python-Based Geospatial Computations

Zachary Sherman, Sandesh Sharma Dulal, Jin-Hee Cho, Mengxi Zhang, Junghwan Kim

ISPRS International Journal of Geo-Information · 18.08.2025 · 14 (8) · 314

DOI: 10.3390/ijgi14080314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 18.08.2025. Verfasst von Zachary Sherman und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute for Society, Culture and Environment (ISCE) at Virginia Tech and OpenAI’s Researcher Access Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the potential of fine-tuned large language models (LLMs) to enhance geospatial intelligence by translating natural language queries into executable Python code. Traditional GIS workflows, while effective, often lack usability and scalability for non-technical users. LLMs offer a new approach by enabling conversational interaction with spatial data. We evaluate OpenAI’s GPT-4o-mini model in two forms: an “As-Is” baseline and a fine-tuned version trained on 600+ prompt–response pairs related to geospatial Python scripting in Virginia. Using U.S. Census shapefiles and hospital data, we tested both models across six types of spatial queries. The fine-tuned model achieved 89.7%, a 49.2 percentage point improvement over the baseline’s 40.5%. It also demonstrated substantial reductions in execution errors and token usage. Key innovations include the integration of spatial reasoning, modular external function calls, and fuzzy geographic input correction. These findings suggest that fine-tuned LLMs can improve the accuracy, efficiency, and usability of geospatial dashboards when they are powered by LLMs. Our results further imply a scalable and replicable approach for future domain-specific AI applications in geospatial science and smart cities studies.

Förderung

  • Institute for Society, Culture and Environment (ISCE) at Virginia Tech and OpenAI’s Researcher Access Program

Zitieren

APA

Sherman, Z., Dulal, S. S., Cho, J., Zhang, M., & Kim, J. (2025). Generative AI for Geospatial Analysis: Fine-Tuning ChatGPT to Convert Natural Language into Python-Based Geospatial Computations. ISPRS International Journal of Geo-Information, 14(8), 314. https://doi.org/10.3390/ijgi14080314

Vancouver

Sherman Z, Dulal SS, Cho J, Zhang M, Kim J. Generative AI for Geospatial Analysis: Fine-Tuning ChatGPT to Convert Natural Language into Python-Based Geospatial Computations. ISPRS International Journal of Geo-Information. 2025;14(8):314. doi:10.3390/ijgi14080314

BibTeX
@article{Sherman2025,
  author = {Sherman, Zachary and Dulal, Sandesh Sharma and Cho, Jin-Hee and Zhang, Mengxi and Kim, Junghwan},
  title = {Generative AI for Geospatial Analysis: Fine-Tuning ChatGPT to Convert Natural Language into Python-Based Geospatial Computations},
  journal = {ISPRS International Journal of Geo-Information},
  year = {2025},
  volume = {14},
  number = {8},
  pages = {314},
  doi = {10.3390/ijgi14080314}
}
Kostenlos starten →