A novel spatio-temporal feature interleaved contrast learning neural network from a robustness perspective

Accurate traffic forecasting is critical to the effectiveness of intelligent transportation systems (ITS) and the development of smart cities.Achieving this goal requires efficient capture of heterogeneous interactions between spatial and temporal dependencies of traffic nodes.However, the robustness and predictive capacity of modeling systems are frequently compromised by the limitations inherent in fine-grained sensor data collection methodologies.Furthermore, the uneven distribution of data can exacerbate the degradation of the model’s predictive performance.To tackle these challenges, we introduce an innovative neural network that leverages spatio-temporal feature interlace contrast learning for daily traffic flow prediction.Our approach consists of two main parts: First, we propose a spatiotemporal position encoder that aims to provide a more balanced sample of training spatiotemporal data with mixed spatial coding to solve the problem of local heterogeneity in the data.Secondly, we employ a spatiotemporal interlace contrast graph structure generator and a specific structure and direction discriminator to discern various potential spatiotemporal features and categorize samples based on trends and consistency, thereby augmenting the system’s robustness and generalization capabilities. Extensive experiments and case studies across six real datasets demonstrate that our approach markedly enhances the prediction accuracy of the baseline model and introduces novel prediction strategies aimed at boosting the system’s robustness.