Parking Availability Prediction via Fusing Multi-Source Data with A Self-Supervised Learning Enhanced Spatio-Temporal Inverted Transformer

2025-09-04

AI Summary

Urban parking scarcity, exacerbated by surging private vehicle ownership, remains inadequately addressed due to limitations in modeling spatiotemporal dependencies and integrating heterogeneous traffic data. To tackle this, we propose a fine-grained parking availability forecasting framework leveraging multi-source transportation data. First, parking zones are adaptively partitioned via K-means clustering. Second, we design a self-supervised enhanced Spatio-Temporal Inverted Transformer featuring dual-branch attention (Series + Channel Attention) to jointly capture long-term temporal dynamics, inter-zone spatial correlations, and multimodal traffic demand interactions. A masked reconstruction pretraining strategy is employed to improve representation robustness. Evaluated on a real-world dataset from Chengdu, our model achieves significantly lower MSE than state-of-the-art baselines—including Informer and Autoformer—with ride-hailing data contributing the largest predictive gain. The framework delivers high-accuracy, actionable insights for intelligent mobility management and urban governance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The rapid growth of private car ownership has worsened the urban parking predicament, underscoring the need for accurate and effective parking availability prediction to support urban planning and management. To address key limitations in modeling spatio-temporal dependencies and exploiting multi-source data for parking availability prediction, this study proposes a novel approach with SST-iTransformer. The methodology leverages K-means clustering to establish parking cluster zones (PCZs), extracting and integrating traffic demand characteristics from various transportation modes (i.e., metro, bus, online ride-hailing, and taxi) associated with the targeted parking lots. Upgraded on vanilla iTransformer, SST-iTransformer integrates masking-reconstruction-based pretext tasks for self-supervised spatio-temporal representation learning, and features an innovative dual-branch attention mechanism: Series Attention captures long-term temporal dependencies via patching operations, while Channel Attention models cross-variate interactions through inverted dimensions. Extensive experiments using real-world data from Chengdu, China, demonstrate that SST-iTransformer outperforms baseline deep learning models (including Informer, Autoformer, Crossformer, and iTransformer), achieving state-of-the-art performance with the lowest mean squared error (MSE) and competitive mean absolute error (MAE). Comprehensive ablation studies quantitatively reveal the relative importance of different data sources: incorporating ride-hailing data provides the largest performance gains, followed by taxi, whereas fixed-route transit features (bus/metro) contribute marginally. Spatial correlation analysis further confirms that excluding historical data from correlated parking lots within PCZs leads to substantial performance degradation, underscoring the importance of modeling spatial dependencies.

Problem

• Predicting urban parking availability using multi-source data
• Modeling spatio-temporal dependencies for parking prediction
• Integrating self-supervised learning with transformer architecture

Innovation

• Self-supervised learning enhanced spatio-temporal transformer
• K-means clustering for parking cluster zones establishment
• Dual-branch attention mechanism for temporal and cross-variate modeling