Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method

• Published in: Transportation research. Part C, Emerging technologies Emerging technologies, 2021-03, Vol.124, p.102928, Article 102928
• Main Authors: Zhang, Jinlei, Che, Hongshu, Chen, Feng, Ma, Wei, He, Zhengbing
• Format: Article
• Language: English
• Subjects: Channel-wise attention; Deep learning; Short-term origin-destination prediction; Split CNN; Urban rail transit
• ISSN: 0968-090X; 1879-2359
• DOI: 10.1016/j.trc.2020.102928

•The unique characteristics of OD flow prediction in the urban railway transit are summarized in detail.•An inflow/outflow-gated mechanism is developed to aggregate historical OD flow information and real-time inflow information.•A split CNN model is introduced to convert the sparse OD flow information to dense and useful features.•A masked loss function is proposed based on the OD attraction degree (ODAD) indicator to handle small or zero OD flows. Short-term origin–destination (OD) flow prediction in urban rail transit (URT) plays a crucial role in smart and real-time URT operation and management. Different from other short-term traffic forecasting methods, the short-term OD flow prediction possesses three unique characteristics: (1) data availability: real-time OD flow is not available during the prediction; (2) data dimensionality: the dimension of the OD flow is much higher than the cardinality of transportation networks; (3) data sparsity: URT OD flow is spatiotemporally sparse. There is a great need to develop novel OD flow forecasting method that explicitly considers the unique characteristics of the URT system. To this end, a channel-wise attentive split–convolutional neural network (CAS-CNN) is proposed. The proposed model consists of many novel components such as the channel-wise attention mechanism and split CNN. In particular, an inflow/outflow-gated mechanism is innovatively introduced to address the data availability issue. We further originally propose a masked loss function to solve the data dimensionality and data sparsity issues. The model interpretability is also discussed in detail. The CAS–CNN model is tested on two large-scale real-world datasets from Beijing Subway, and it outperforms the rest of benchmarking methods. The proposed model contributes to the development of short-term OD flow prediction, and it also lays the foundations of real-time URT operation and management.