Spatio-temporal forecasting of traffic flow data represents a typical problem in the field of machine learning, impacting urban traffic management systems. Traditional statistical and machine learning methods cannot adequately handle both the temporal and spatial dependencies in these complex traffic flow datasets. A prevalent approach in the field is to combine graph convolutional networks and multi-head attention mechanisms for spatio-temporal processing. This paper proposes a wavelet-based temporal attention model, namely a wavelet-based dynamic spatio-temporal aware graph neural network (W-DSTAGNN), for tackling the traffic forecasting problem. Benchmark experiments using several statistical metrics confirm that our proposal efficiently captures spatio-temporal correlations and outperforms ten state-of-the-art models on three different real-world traffic datasets. Our proposed ensemble data-driven method can handle dynamic temporal and spatial dependencies and make long-term forecasts in an efficient manner.

翻译：交通流量数据的时空预测是机器学习领域的一个典型问题，对城市交通管理系统具有重要影响。传统的统计与机器学习方法难以充分处理这些复杂交通流量数据集中同时存在的时间与空间依赖性。该领域的主流方法通常结合图卷积网络与多头注意力机制进行时空处理。本文提出一种基于小波的时间注意力模型——基于小波的动态时空感知图神经网络（W-DSTAGNN），用于解决交通预测问题。采用多种统计指标的基准实验证实，我们的方案能有效捕捉时空相关性，并在三个真实交通数据集上超越了十种先进模型。我们提出的集成数据驱动方法能够处理动态时空依赖性，并以高效方式实现长期预测。