Detecting Urban Clues for Road Safety : Leveraging Big Data and Machine Learning in World Bank Transport Projects
Transportation services and infrastructure connect people, businesses, and places. They allow citizens to access opportunities, such as jobs, education, health services, recreation, and enable the movement and distribution of goods. As a result, transp...
| Main Author: | |
|---|---|
| Format: | Report |
| Language: | English |
| Published: |
Washington, DC: World Bank
2022
|
| Online Access: | http://documents.worldbank.org/curated/en/099200002152228754/P170812020245f053097a50eeba0230ef35 http://hdl.handle.net/10986/37043 |
| Summary: | Transportation services and
infrastructure connect people, businesses, and places. They
allow citizens to access opportunities, such as jobs,
education, health services, recreation, and enable the
movement and distribution of goods. As a result, transport
services and infrastructure are key to the economic
development of cities and regions. While the development of
transportation systems and infrastructure is vital to
economic growth, it is also important to evaluate and
mitigate its potential negative externalities and costs to
society. The purpose of this guidance note is to provide
concrete guidance on how big data and machine learning (ML)
can be leveraged in road safety analysis. The document
presents opportunities to use these new technologies to
improve current road safety assessment procedures across the
project cycle, in accordance with the World Bank’s latest
Environmental and Social Framework (ESF) guidelines. This
guidance note is for World Bank task teams who are
interested in using new data sources and analytical methods
for road safety analysis across various types of projects.
This document consists of three parts. Part 1 discusses the
World Bank’s current guidelines for incorporating road
safety analysis across the project cycle, examines existing
data and approaches and identifies opportunities to improve
current methods using big data and ML. Part 2 provides an
overview of these new technologies and concrete guidance on
how they can be integrated into World Bank projects. Part 3
presents case studies on two regions of interest – Bogotá,
Colombia and Padang, Indonesia to demonstrate how ML can be
implemented to evaluate road safety. The document concludes
with recommendations for using big data and ML in road
safety assessments in the future. |
|---|