DualCast: A Model to Disentangle Aperiodic Events from Traffic Series
This addresses the problem of inaccurate traffic forecasting for transportation systems by improving handling of aperiodic events, representing an incremental advance over existing methods.
The paper tackles the problem of traffic forecasting models overlooking critical aperiodic events like traffic incidents by proposing DualCast, a dual-branch framework that disentangles traffic signals into intrinsic spatial-temporal patterns and external environmental contexts. The result is a versatile model that reduces forecasting errors by up to 9.6% when integrated with existing models on multiple real datasets.
Traffic forecasting is crucial for transportation systems optimisation. Current models minimise the mean forecasting errors, often favouring periodic events prevalent in the training data, while overlooking critical aperiodic ones like traffic incidents. To address this, we propose DualCast, a dual-branch framework that disentangles traffic signals into intrinsic spatial-temporal patterns and external environmental contexts, including aperiodic events. DualCast also employs a cross-time attention mechanism to capture high-order spatial-temporal relationships from both periodic and aperiodic patterns. DualCast is versatile. We integrate it with recent traffic forecasting models, consistently reducing their forecasting errors by up to 9.6% on multiple real datasets. Our source code is available at https://github.com/suzy0223/DualCast.