Saved in:
Bibliographic Details
Main Author: Ivchenko, Anton
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.04242
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910192751345664
author Ivchenko, Anton
author_facet Ivchenko, Anton
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04242
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Road Risk Monitor: A Deployable U.S. Road Incident Forecasting System with Live Weather and Road-Level Tiles
Ivchenko, Anton
Machine Learning
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.
title Road Risk Monitor: A Deployable U.S. Road Incident Forecasting System with Live Weather and Road-Level Tiles
topic Machine Learning
url https://arxiv.org/abs/2605.04242