cs.AINov 9, 2026

Beyond Sunny Skies: Using Large Language Models to Predict Urban Traffic in Adverse Weather

Authors: Zhu Xiao, Kuan Feng, Tong Li, Chenxi Liu, Gang Wang, Zhuo Tang, Kenli Li

Organizations: College of Computer Science and Electronic Engineering, the Ministry of Education Key Laboratory of “Fusion Computing of Supercomputing and Artificial Intelligence”, Hunan University, Changsha 410082, China. · Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong. · CETC Key Laboratory of Aerospace Information Applications, Shijiazhuang, China.

Abstract

Urban traffic flow prediction is a cornerstone of intelligent transportation systems, yet accurate forecasting under adverse weather conditions remains a significant challenge. Existing data-driven models, while effective for routine patterns, often struggle with the sparse data and complex non-linear shifts associated with rare meteorological events. These methods typically treat environmental contexts as shallow numerical features, failing to capture the underlying semantic reasoning-why and how specific adverse conditions alter mobility behaviors across regions with different functional compositions. To address this limitation, we propose Multi-STG, a unified framework that integrates Large Language Model (LLM)-derived semantic priors with graph-based spatiotemporal learning. Multi-STG introduces an LLM-empowered semantic enhancement module that transforms comprehensive context descriptions such as weather, POIs, and holidays into high-level semantic embeddings, effectively providing a knowledge-driven complement to data scarcity. Furthermore, we design a multimodal attentional fusion mechanism to dynamically weigh heterogeneous inputs and a semantic-enhanced prediction head with gated residual calibration to robustly adjust forecasts based on semantic guidance. Extensive experiments on real-world multi-city private car datasets demonstrate that Multi-STG outperforms state-of-the-art baselines, reducing MAE by 11.82% on average relative to the strongest baseline across three cities, while maintaining stable performance under sparse and non-stationary conditions.

Figures & tables

Explore similar work

CardsList
  1. A Dynamic Fusion Large Language Model for Traffic Flow Prediction

    Sep 10, 2026Xue Qiu, Jianli XiaoIntelligent Transportation SystemsTraffic Flow Estimation

  2. Unveiling Stochasticity: Universal Multi-modal Probabilistic Modeling for Traffic Forecasting

    Apr 17, 2026Weijiang Xiong, Robert Fonod, Nikolas GeroliminisTraffic ForecastingProbabilistic Time Series Forecasting

  3. LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction

    Oct 2, 2026Xuxilu Zhang, Francesc SorigueraSpatiotemporal ForecastingTime Series Forecasting