Road Risk Monitor: A Deployable U.S. Road Incident Forecasting System with Live Weather and Road-Level Tiles
This work addresses the practical challenge of building an end-to-end, nationwide road-incident forecasting system for real-world deployment, but the modeling approach is incremental.
Road Risk Monitor is a deployable system for forecasting road incidents across the U.S. by integrating historical crash data, live weather, and road geometry into a pipeline that serves predictions via APIs and a web app. The system achieves a baseline using FARS data and a road-segment model from US-Accidents events.
Nationwide road-incident forecasting is a systems problem before it is a modeling problem. A usable service must connect historical incident archives, historicalandliveweather,nationalroadgeometry, offline model training, tile generation, web serving and runtime handoff. This paper presents Road Risk Monitor, a U.S.-wide road-safety stack that combines a nationwide H3 baseline trained on FARS fatal-crash data with a road-segment forecasting pipeline trained from TIGER/Line geometry and US-Accidents events, then serves predictions through live APIs, raster tiles, JSON road tiles, and a public web application.