|
Activity Number:
|
432
- Contributed Poster Presentations: Royal Statistical Society
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 10, 2022 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Royal Statistical Society
|
|
Abstract #322623
|
|
|
Title:
|
Traffic Risk Mapping Using Enhanced Stochastic Partial Differential Equations (SPDE) Approach
|
|
Author(s):
|
Somnath Chaudhuri and Pablo Juan and Diego Varga and Maria A Barceló and Marc Saez*
|
|
Companies:
|
University of Girona, Spain and CIBERESP and University Jaume I, Spain and University of Girona, Spain and CIBERESP and University of Girona, Spain and CIBERESP and University of Girona, Spain and CIBERESP
|
|
Keywords:
|
Bayesian Inference;
Traffic risk;
INLA-SPDE
|
|
Abstract:
|
Over the past few years, traffic collisions have been one of the serious issues all over the world. The current study proposes a spatio-temporal model that can make predictions regarding the number of road casualties on individual road segments and can generate a risk map of the entire road network. Bayesian methodology using Integrated Nested Laplace Approximation (INLA) with Stochastic Partial Differential Equations (SPDE) has been applied in the modeling process. The novelty of the proposed model is to introduce SPDE network triangulation to estimate the spatial autocorrelation of discrete events precisely on linear networks. In broader picture, the study contributes to the relatively small amount of literature on enhanced INLA-SPDE modeling of spatial point processes precisely on road networks. The result risk maps can have strategic application in developing GIS analytical tools to identify and depict possible safe routes. The maps can also have implications for accident prevention and multi-disciplinary road safety measures through an enhanced understanding of the accident patterns and factors. The methodology can be adapted and applied to other locations globally.
|
Authors who are presenting talks have a * after their name.
