Information and Communications Technology

This deep learning model can help prevent traffic crashes - here's how it works

Oct 18, 2021

this is a sky view of a road in Los Angeles. Out of the 4 cities examined by scientists in a study on traffic crashes, LA had the highest crash density

“If people can use the risk map to identify potentially high-risk road segments, they can take action in advance to reduce the risk of trips they take." - MIT CSAIL PhD student Songtao He. Image: UNSPLASH/Kyle Murfin

Rachel Gordon

Writer, MIT News

Our Impact

The Big Picture

Explore and monitor how Information and Communications Technology is affecting economies, industries and global issues

A hand holding a looking glass by a lake

Crowdsource Innovation

Get involved with our crowdsourced digital platform to deliver impact at scale

Stay up to date:

Information and Communications Technology

shown here is a dataset that was used to create crash-risk maps covered 7,500 square kilometers from Los Angeles, New York City, Chicago and Boston

Caption:A dataset that was used to create crash-risk maps covered 7,500 square kilometers from Los Angeles, New York City, Chicago and Boston. Among the four cities, L.A. was the most unsafe, since it had the highest crash density, followed by New York City, Chicago, and Boston Image: MIT CSAIL

shown here is a diagram crashes and data from 2017 and 2018, used by the scientists to create their model

To evaluate the model, the scientists used crashes and data from 2017 and 2018, and tested its performance at predicting crashes in 2019 and 2020. Many locations were identified as high-risk, even though they had no recorded crashes, and also experienced crashes during the follow-up years. Image: MIT CSAIL

Have you read?

Don't miss any update on this topic

Create a free account and access your personalized content collection with our latest publications and analyses.

License and Republishing

World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.

The views expressed in this article are those of the author alone and not the World Economic Forum.