Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Urban Computing in the Era of Large Language Models

Zhonghang Li, Lianghao Xia, Xubin Ren, Jiabin Tang, Tianyi Chen, Yong Xu, Chao Huang

TL;DR

This survey addresses how large language models can transform urban computing by addressing data heterogeneity, planning, and citizen engagement. It analyzes foundational LLM technologies and articulates a nine-domain taxonomy of urban applications, detailing how LLMs act as encoders, predictors, agents, enhancers, and assistants across transportation, public safety, mobility, environment, travel, urban planning, energy, geoscience, and autonomous driving. The authors compile datasets and evaluation methods to accelerate experimentation, discuss implementation patterns, and propose LLM-based solutions to unresolved challenges such as generalization, interpretability, and efficiency. The work highlights the potential for LLMs to improve decision-making, resilience, and citizen-facing services in smart cities, while outlining practical research directions to realize these benefits safely and efficiently.

Abstract

Urban computing has emerged as a multidisciplinary field that harnesses data-driven technologies to address challenges and improve urban living. Traditional approaches, while beneficial, often face challenges with generalization, scalability, and contextual understanding. The advent of Large Language Models (LLMs) offers transformative potential in this domain. This survey explores the intersection of LLMs and urban computing, emphasizing the impact of LLMs in processing and analyzing urban data, enhancing decision-making, and fostering citizen engagement. We provide a concise overview of the evolution and core technologies of LLMs. Additionally, we survey their applications across key urban domains, such as transportation, public safety, and environmental monitoring, summarizing essential tasks and prior works in various urban contexts, while highlighting LLMs' functional roles and implementation patterns. Building on this, we propose potential LLM-based solutions to address unresolved challenges. To facilitate in-depth research, we compile a list of available datasets and tools applicable to diverse urban scenarios. Finally, we discuss the limitations of current approaches and outline future directions for advancing LLMs in urban computing.

Urban Computing in the Era of Large Language Models

TL;DR

This survey addresses how large language models can transform urban computing by addressing data heterogeneity, planning, and citizen engagement. It analyzes foundational LLM technologies and articulates a nine-domain taxonomy of urban applications, detailing how LLMs act as encoders, predictors, agents, enhancers, and assistants across transportation, public safety, mobility, environment, travel, urban planning, energy, geoscience, and autonomous driving. The authors compile datasets and evaluation methods to accelerate experimentation, discuss implementation patterns, and propose LLM-based solutions to unresolved challenges such as generalization, interpretability, and efficiency. The work highlights the potential for LLMs to improve decision-making, resilience, and citizen-facing services in smart cities, while outlining practical research directions to realize these benefits safely and efficiently.

Abstract

Urban computing has emerged as a multidisciplinary field that harnesses data-driven technologies to address challenges and improve urban living. Traditional approaches, while beneficial, often face challenges with generalization, scalability, and contextual understanding. The advent of Large Language Models (LLMs) offers transformative potential in this domain. This survey explores the intersection of LLMs and urban computing, emphasizing the impact of LLMs in processing and analyzing urban data, enhancing decision-making, and fostering citizen engagement. We provide a concise overview of the evolution and core technologies of LLMs. Additionally, we survey their applications across key urban domains, such as transportation, public safety, and environmental monitoring, summarizing essential tasks and prior works in various urban contexts, while highlighting LLMs' functional roles and implementation patterns. Building on this, we propose potential LLM-based solutions to address unresolved challenges. To facilitate in-depth research, we compile a list of available datasets and tools applicable to diverse urban scenarios. Finally, we discuss the limitations of current approaches and outline future directions for advancing LLMs in urban computing.

Paper Structure

This paper contains 32 sections, 3 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Large Language Models (LLMs)
  4. Pioneering Technologies in LLMs Progress
  5. Urban computing with LLMs
  6. Intelligent Transportation Systems
  7. Traffic prediction
  8. Traffic management
  9. Future-Proofing Intelligent Transportation Systems
  10. Public Safety
  11. Urban Mobility
  12. Environmental Monitoring
  13. Travel planning
  14. Urban Planning and Development
  15. Smart Energy Management
  16. ...and 17 more sections

Figures (3)

  • Figure 1: A sketch shows the evolution of urban computing technologies. The rapid advancement of Internet of Things (IoT) technologies and database enriched urban data (left). Despite deep learning techniques efficiently analyzing this data and producing useful insights, they struggle with multimodal data and autonomous planning (middle). The recent introduction of LLMs has advanced urban computing, highlighting their potential to improve urban efficiency (right).
  • Figure 2: Various applications of LLMs within urban computing.
  • Figure 3: We categorize the roles of LLMs in urban computing into five functional types: encoder, predictor, enhancer, assistant, and agent.