

























Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.04242 [cs.LG] |
| (or arXiv:2605.04242v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.04242 arXiv-issued DOI via DataCite (pending registration) |
From: Anton Ivchenko [view email]
[v1]
Tue, 5 May 2026 19:30:06 UTC (163 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。