Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 10, 2026SustainabilityOpen Access

A Multi-Model Machine Learning Framework for Predicting and Ranking High-Risk Urban Intersections in Riyadh

View Full Paper
Ask AI
Bookmark
Share

Authors

SASaleh AltwaijriSASaleh AlotaibiFAFaisal Alosaimi

Discussion

Loading...

Member takes

Overview

Develops a machine learning framework to predict accident severity in urban intersections, suggesting infrastructure improvements.

Key Points

  • The study aims to predict intersection accident severity using machine learning techniques and historical data from Riyadh.
  • Analyzed historical data (2017–2023) from Riyadh Municipality for 150 high-risk intersections.
  • Incorporated predictors such as service road distance, U-turn distance, and peak hour volume.
  • Compared six machine learning algorithms using a 70/30 train–test split and k-fold cross-validation.
  • Selected Gradient Boosting model based on performance metrics.
  • The Gradient Boosting model yielded R2 = 0.89, MSE = 63.43, and RMSE = 7.96.
  • Identified minor injuries, serious injuries, and fatalities as key predictors of accident severity.
  • Ranked the ‘Jeddah Road with Taif Road’ as the highest-risk location with a predicted EPDO of 137.22.

Cite This Study

Altwaijri et al. (2026) studied this question.

synapsesocial.com/papers/69d896406c1944d70ce078e4https://doi.org/10.3390/su18083651
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Modeling Driver-Caused Road Crash Severity Using SHAP-Enhanced Machine Learning2026
  2. 2Crash severity determinants in Saudi Arabia’s Eastern Province: Evidence from logistic regression and neural networks2026
  3. 3Comparative evaluation of deep learning and traditional models for predicting traffic accident severity in Saudi Arabia2025
  4. 4Improving road safety in smart cities using machine learning techniques2026
  5. 5An Integrated explainable machine learning framework for pavement condition assessment and maintenance prioritization: A Saudi Arabian case study2026