TERMCast: Temporal Relation Modeling for Effective Urban Flow Forecasting

TL;DR

TERMCast is a novel Transformer-based architecture that jointly models periodicity, closeness, and trend components for urban flow forecasting, significantly improving prediction accuracy by explicitly capturing long-term relations.

Contribution

It introduces a unified model that simultaneously incorporates periodicity, closeness, and trend components, with a dedicated relation prediction and consistency mechanism.

Findings

Outperforms state-of-the-art methods on three datasets.

Effectiveness of the relation prediction module is validated.

Consistency loss improves forecasting accuracy.

Abstract

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.