CIWI-CKT: Chaos-Informed Wave Interference Feature Fusion and Cross-City Knowledge Transfer for Traffic Flow Forecasting

2026-06-14

AI Summary

This work addresses the challenge of model generalization in traffic flow prediction under cross-city, data-scarce scenarios, where limited historical data, inherent traffic chaos, and heterogeneous urban network structures impede performance. To tackle this, the authors propose a chaos-guided adaptive wave modeling approach that integrates chaos invariant extraction, wave interference mechanisms, and meta-learning to construct a few-shot transfer framework with theoretical stability guarantees and bounded generalization error. Evaluated on four real-world datasets, the proposed method significantly outperforms existing models, achieving higher prediction accuracy while requiring substantially less training data.

Abstract

Accurate traffic flow prediction remains challenging in cross-city, data-scarce scenarios where limited historical data hinders model generalisation. The chaotic nature of traffic dynamics, complex spatio-temporal dependencies, and heterogeneous urban networks complicate few-shot learning across cities. Existing deep learning approaches either treat traffic as purely deterministic or lack mechanisms to model wave-like interference patterns essential for cross-regime traffic dynamics. To address these limitations, this paper proposes CIWI-CKT, a novel Chaos-Informed Wave Interference Feature Fusion framework with Cross-City Knowledge Transfer. Our framework introduces three core innovations: chaos-informed wave generation that extracts measurable chaos invariants and models traffic as adaptive wave components; meta-interference processing that captures wave interactions between support and query regimes while producing a predictability score for confidence estimation; and chaos-aware meta-learning that enables efficient cross-city knowledge transfer while preserving chaotic characteristics. We establish theoretical guarantees including chaos-to-wave stability, wave-induced dimension reduction, and meta-learning generalisation bounds. Extensive experiments on four real-world traffic datasets demonstrate that CIWI-CKT significantly outperforms state-of-the-art spatio-temporal graph learning, transfer learning, prompt-based, and few-shot methods, improving prediction accuracy while substantially reducing required training data.

Problem

• traffic flow forecasting
• cross-city
• data scarcity
• chaotic dynamics
• spatio-temporal dependencies

Innovation

• chaos-informed wave
• wave interference
• cross-city knowledge transfer
• meta-learning
• traffic flow forecasting