# Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models

arXiv: https://arxiv.org/abs/2410.20975 · HTML: https://mlsanity.com/paper/2410.20975/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 44 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [Software Testing with Large Language Models: Survey, Landscape, and Vision](https://mlsanity.com/paper/2307.07221/) (2023)
- [Large Language Models in Law: A Survey](https://mlsanity.com/paper/2312.03718/) (2023)
- [Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents](https://mlsanity.com/paper/2105.03887/) (2021)
- [LEVA: Using Large Language Models to Enhance Visual Analytics](https://mlsanity.com/paper/2403.05816/) (2024)
- [GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks](https://mlsanity.com/paper/2410.17031/) (2024)
- [Evaluation of Code LLMs on Geospatial Code Generation](https://mlsanity.com/paper/2410.04617/) (2024)
- [An Improved Apriori Algorithm for Association Rules](https://mlsanity.com/paper/1403.3948/) (2014)
- [PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation](https://mlsanity.com/paper/2210.03496/) (2022)

## Built on by (most cited first, 1 of 1)

- [GeoSQL-Eval: First Evaluation of LLMs on PostGIS-Based NL2GeoSQL Queries](https://mlsanity.com/paper/2509.25264/) (2025)

## Abstract (arXiv)

The rise of spatiotemporal data and the need for efficient geospatial modeling have spurred interest in automating these tasks with large language models (LLMs). However, general LLMs often generate errors in geospatial code due to a lack of domain-specific knowledge on functions and operators. To address this, a retrieval-augmented generation (RAG) approach, utilizing an external knowledge base of geospatial functions and operators, is proposed. This study introduces a framework to construct such a knowledge base, leveraging geospatial script semantics. The framework includes: Function Semantic Framework Construction (Geo-FuSE), Frequent Operator Combination Statistics (Geo-FuST), and Semantic Mapping (Geo-FuM). Techniques like Chain-of-Thought, TF-IDF, and the APRIORI algorithm are utilized to derive and align geospatial functions. An example knowledge base, Geo-FuB, built from 154,075 Google Earth Engine scripts, is available on GitHub. Evaluation metrics show a high accuracy, reaching 88.89% overall, with structural and semantic accuracies of 92.03% and 86.79% respectively. Geo-FuB's potential to optimize geospatial code generation through the RAG and fine-tuning paradigms is highlighted.