CAST-CKT: Chaos-Aware Spatio-Temporal and Cross-City Knowledge Transfer for Traffic Flow Prediction

2026-02-04

AI Summary

This work addresses the challenges of nonlinear dynamics and domain shift in cross-city traffic flow forecasting under data-scarce conditions by proposing a spatiotemporal knowledge transfer framework integrated with a chaos-aware mechanism. The approach introduces a chaos analyzer to quantify the predictability state of traffic systems and innovatively designs a chaos-aware attention mechanism, an adaptive topology learning module, and a cross-city alignment strategy grounded in chaos consistency. These components jointly enable adaptive temporal modeling, dynamic spatial dependency capture, and uncertainty-aware multi-step prediction. Evaluated on four cross-city few-shot benchmarks, the model significantly outperforms existing methods, achieving substantial reductions in MAE and RMSE while offering interpretable insights into chaotic states, thereby enhancing generalization under limited data.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Transportation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Traffic prediction in data-scarce, cross-city settings is challenging due to complex nonlinear dynamics and domain shifts. Existing methods often fail to capture traffic's inherent chaotic nature for effective few-shot learning. We propose CAST-CKT, a novel Chaos-Aware Spatio-Temporal and Cross-City Knowledge Transfer framework. It employs an efficient chaotic analyser to quantify traffic predictability regimes, driving several key innovations: chaos-aware attention for regime-adaptive temporal modelling; adaptive topology learning for dynamic spatial dependencies; and chaotic consistency-based cross-city alignment for knowledge transfer. The framework also provides horizon-specific predictions with uncertainty quantification. Theoretical analysis shows improved generalisation bounds. Extensive experiments on four benchmarks in cross-city few-shot settings show CAST-CKT outperforms state-of-the-art methods by significant margins in MAE and RMSE, while offering interpretable regime analysis. Code is available at https://github.com/afofanah/CAST-CKT.

Problem

• traffic flow prediction
• cross-city
• data scarcity
• chaotic dynamics
• few-shot learning

Innovation

• chaos-aware attention
• adaptive topology learning
• cross-city knowledge transfer
• chaotic consistency
• few-shot traffic prediction