LSDTs: LLM-Augmented Semantic Digital Twins for Adaptive Knowledge-Intensive Infrastructure Planning

TL;DR

LSDTs leverage LLMs to extract and organize unstructured knowledge into semantic digital twins, enabling regulation-aware, adaptable infrastructure planning and simulation.

Contribution

This work introduces LSDTs, a novel framework integrating LLMs with digital twins to handle unstructured knowledge for infrastructure planning.

Findings

Supports regulation-aware layout optimization

Enables high-fidelity simulation of planning scenarios

Enhances adaptability in infrastructure management

Abstract

Digital Twins (DTs) offer powerful tools for managing complex infrastructure systems, but their effectiveness is often limited by challenges in integrating unstructured knowledge. Recent advances in Large Language Models (LLMs) bring new potential to address this gap, with strong abilities in extracting and organizing diverse textual information. We therefore propose LSDTs (LLM-Augmented Semantic Digital Twins), a framework that helps LLMs extract planning knowledge from unstructured documents like environmental regulations and technical guidelines, and organize it into a formal ontology. This ontology forms a semantic layer that powers a digital twin-a virtual model of the physical system-allowing it to simulate realistic, regulation-aware planning scenarios. We evaluate LSDTs through a case study of offshore wind farm planning in Maryland, including its application during Hurricane Sandy. Results demonstrate that LSDTs support interpretable, regulation-aware layout optimization, enable high-fidelity simulation, and enhance adaptability in infrastructure planning. This work shows the potential of combining generative AI with digital twins to support complex, knowledge-driven planning tasks.