LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data

TL;DR

LISA is a novel framework that jointly learns space partitions and traffic accident prediction models, effectively capturing heterogeneous patterns across different scales and improving forecasting accuracy.

Contribution

The paper introduces a learning-integrated space partitioning framework that dynamically adapts partitions during model training based on prediction accuracy.

Findings

Achieves an average of 13.0% improvement over baseline models.

Effectively captures heterogeneous accident patterns across multiple scales.

Demonstrates self-guided partitioning without external knowledge.

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%.