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

2025-08-08

AI Summary

Existing digital twin (DT) approaches struggle to effectively integrate unstructured textual knowledge—such as environmental regulations and technical guidelines—thereby limiting regulatory compliance and adaptive capability in infrastructure planning. To address this, we propose a semantics-enhanced digital twin framework that synergistically integrates large language models (LLMs) with ontology-based modeling to enable automated extraction, interpretable rule embedding, and semantic organization of unstructured knowledge. The framework supports high-fidelity, compliance-aware adaptive planning simulation and ensures transparent reasoning and decision-making under dynamic environmental conditions. Evaluated on the Maryland offshore wind energy planning case, the framework generates normatively compliant and human-interpretable layout configurations, and successfully reproduces emergency response processes under Hurricane Sandy scenarios. Results demonstrate significant improvements in planning authenticity, flexibility, and stakeholder trustworthiness.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Integrating unstructured knowledge into Digital Twins effectively
• Extracting planning knowledge from diverse unstructured documents
• Enhancing adaptability in infrastructure planning with LLMs

Innovation

• LLMs extract knowledge from unstructured documents
• Organize knowledge into formal ontology layer
• Digital twins simulate regulation-aware scenarios