Forecasting the Emergence and Evolution of Crash Hotspots: A Unified Deep Learning Framework for Proactive Traffic Safety

2026-07-27

AI Summary

This study addresses the limitations of traditional traffic crash hotspot management, which relies on static historical data and struggles to identify or predict dynamically evolving emerging hotspots. To overcome this, the authors propose HERALD, a unified deep learning framework that models hotspots as dynamic events for the first time. HERALD integrates CNN and Transformer architectures, incorporates a mixture-of-experts mechanism to account for urban–rural disparities, and leverages a self-exciting point process with geographic risk anchoring to enable weekly hotspot detection, future location prediction, and interpretable tracking across the entire hotspot lifecycle. Experiments across six heterogeneous counties in Wisconsin demonstrate that HERALD significantly outperforms five baseline models in both localization accuracy and early-warning capability, while supporting adjustable sensitivity to meet diverse deployment requirements.

Abstract

Road crashes remain among the gravest threats to public safety, and preventing them is a defining task of transportation systems worldwide. Much of that harm concentrates at hotspots, yet a hotspot is less a place than an episode; it emerges quietly at an intersection or along an arterial, intensifies for weeks, then subsides, only to reappear elsewhere. Enforcement guided by maps of past crashes inevitably trails this cycle, patrolling yesterday's hotspots while tomorrow's form unwatched. Breaking that lag requires three capabilities at once: detecting hotspots as they are born, forecasting where they will sit next week, and following each one through its life. We introduce HERALD (Hotspot Emergence, Risk Anticipation, and Life-cycle Dynamics), a unified deep learning framework that provides all three from a single statewide model. HERALD distills each county's recent crash history into weekly risk maps and forecasts the next with a CNN--Transformer, whose mixture-of-experts lets one model serve dense urban cores and sparse rural corridors alike. Each forecast is anchored in the county's long-run crash geography, sharpened by the self-exciting effect of recent crashes, and paired with explicit warnings of where new hotspots are about to appear. Followed over time, every hotspot acquires a legible life story, from birth through growth and stability to decline and death. Across six heterogeneous Wisconsin counties, HERALD forecasts more accurately than five identically trained baselines, locates hotspots most precisely, and flags emerging risks before they take hold. A single adjustable setting trades accuracy for extra sensitivity where deployment demands it. The result shifts hotspot management from mapping the past to anticipating the future.

Problem

• crash hotspots
• forecasting
• traffic safety
• emergence
• life-cycle dynamics

Innovation

• hotspot forecasting
• deep learning
• CNN-Transformer
• mixture-of-experts
• traffic safety