LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data
Bang An, Xun Zhou, Amin Vahedian, Nick Street, Jinping Guan, Jun Luo
TL;DR
This work tackles traffic accident forecasting in heterogeneous spaces by introducing Learning-Integrated Space Partitioning (LISA), a framework that learns space partitions and prediction models simultaneously. It combines Integrated Hierarchical Partitioning Training (I-HPT) with a Partition Learner (PL) and an optional Spatial Gradient Search to form homogeneous sub-regions while training, guiding partitioning by prediction error. Compared against a broad set of baselines across multiple deep networks, LISA yields an average improvement of 13% in predictive accuracy and demonstrates stronger spatial correlation with ground truth, especially in highly heterogeneous regions. The approach is network-agnostic and can leverage various spatiotemporal models, enabling automatic, data-driven partitioning that adapts to underlying patterns and improves practical traffic safety and emergency-response forecasting.
Abstract
Traffic accident forecasting is an important task for intelligent transportation management and emergency response systems. However, this problem is challenging due to the spatial heterogeneity of the environment. Existing data-driven methods mostly focus on studying homogeneous areas with limited size (e.g. a single urban area such as New York City) and fail to handle the heterogeneous accident patterns over space at different scales. Recent advances (e.g. spatial ensemble) utilize pre-defined space partitions and learn multiple models to improve prediction accuracy. However, external knowledge is required to define proper space partitions before training models and pre-defined partitions may not necessarily reduce the heterogeneity. To address this issue, we propose a novel Learning-Integrated Space Partition Framework (LISA) to simultaneously learn partitions while training models, where the partitioning process and learning process are integrated in a way that partitioning is guided explicitly by prediction accuracy rather than other factors. Experiments using real-world datasets, demonstrate that our work can capture underlying heterogeneous patterns in a self-guided way and substantially improve baseline networks by an average of 13.0%.