Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.081652
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Knowledge Graph-Driven Training Data Construction for Urban Flood-Traffic Scenario Generation Using Small Language Models

Geunhwi Park1, Juneyoung Park2,*, Chunjoo Yoon3, Jaehong Park3
1 Department of Smart City Engineering, Hanyang University, Ansan-si, Republic of Korea
2 Department of Transportation and Logistics Engineering, Hanyang University, Ansan-si, Republic of Korea
3 Department of Highway & Transportation Research, Korea Institute of Civil Engineering and Building Technology, Goyang-si, Republic of Korea
* Corresponding Author: Juneyoung Park. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.081652

Received 06 March 2026; Accepted 14 May 2026; Published online 29 May 2026

Abstract

Urban flooding caused by extreme rainfall events disrupts transportation systems, yet generating realistic flood-traffic scenarios for disaster preparedness remains a labor-intensive manual process. This study proposes a Knowledge Graph (KG)-driven pipeline that automatically generates domain-specific training data for fine-tuning small language models (sLLMs) to synthesize urban flood-traffic scenarios. A domain KG comprising 58 entities and 285 relationships was constructed for Jinju City, South Korea, integrating empirical flood data from 112 local documents with quantitative rainfall-traffic impact values from 14 international studies. Nine domain constraint rules, including a novel spatial consistency rule, ensure the physical plausibility of generated scenarios. Through constrained weighted graph walks, 800 semi-structured English narrative scenarios were automatically generated in approximately 5 min, substantially reducing the labor required compared to manual creation. Three sLLMs spanning different architectures and parameter scales—Flan-T5-Large (770M), Qwen2.5-3B-Instruct (3B), and Qwen2.5-7B-Instruct (7B)—were fine-tuned using QLoRA on a single GPU with 16 GB VRAM. Evaluation on 78 test samples demonstrated consistent performance improvements with increasing model scale: Qwen2.5-7B achieved BLEU-4 of 0.5524, ROUGE-L of 0.6883, BERTScore F1 of 0.9662, and KG Fact Consistency of 1.0000, representing a 33.8% BLEU-4 improvement over Flan-T5-Large. Both Qwen models achieved KG Fact Consistency of 1.0000. The 3B model achieved 98.6% of the 7B model’s BLEU-4 at 53% of the VRAM cost with identical factual consistency, representing the most cost-effective configuration. All models were trained for 10 epochs on the same GPU, demonstrating practical feasibility for municipal disaster response deployment.

Keywords

Knowledge graph; training data generation; urban flood; traffic scenario; small language model; fine-tuning; text generation; QLoRA

  • 133

    View

  • 23

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link