Urban flow forecasting is a challenging task, given the inherent periodic characteristics of urban flow patterns. To capture the periodicity, existing urban flow prediction approaches are often designed with closeness, period, and trend components extracted from the urban flow sequence. However, these three components are often considered separately in the prediction model. These components have not been fully explored together and simultaneously incorporated in urban flow forecasting models. We introduce a novel urban flow forecasting architecture, TERMCast. A Transformer based long-term relation prediction module is explicitly designed to discover the periodicity and enable the three components to be jointly modeled This module predicts the periodic relation which is then used to yield the predicted urban flow tensor. To measure the consistency of the predicted periodic relation vector and the relation vector inferred from the predicted urban flow tensor, we propose a consistency module. A consistency loss is introduced in the training process to further improve the prediction performance. Through extensive experiments on three real-world datasets, we demonstrate that TERMCast outperforms multiple state-of-the-art methods. The effectiveness of each module in TERMCast has also been investigated.
@inproceedings{xue2021termcast,
title={Termcast: Temporal relation modeling for effective urban flow forecasting},
author={Xue, Hao and Salim, Flora D},
booktitle={Pacific-Asia Conference on Knowledge Discovery and Data Mining},
pages={741--753},
year={2021},
organization={Springer}
}
© 2021 Flora Salim - CRUISE Research Group.