The path most traveled: travel demand estimation using big data resources

• Autor(a) principal: Toole, Jameson L.
• Data de Publicação: 2016
• Outros Autores: Colak, Serdar, Sturt, Bradley, Alexander, Lauren P., Evsukoff, Alexandre Gonçalves, González, Marta C.
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional do FGV (FGV Repositório Digital)
• Texto Completo: http://hdl.handle.net/10438/24893
• topic: Mobility; Location based services; Congestion; Road networks; Mobile phone data; Matemática; Mobilidade urbana - Métodos estatísticos - Processamento de dados; Big data; Mineração de dados (Computação)

Rapid urbanization is placing increasing stress on already burdened transportation infrastructure. Ubiquitous mobile computing and the massive data it generates presents new opportunities to measure the demand for this infrastructure, diagnose problems, and plan for the future. However, before these benefits can be realized, methods and models must be updated to integrate these new data sources into existing urban and transportation planning frameworks for estimating travel demand and infrastructure usage. While recent work has made great progress extracting valid and useful measurements from new data resources, few present end-to-end solutions that transform and integrate raw, massive data into estimates of travel demand and infrastructure performance. Here we present a flexible, modular, and computationally efficient software system to fill this gap. Our system estimates multiple aspects of travel demand using call detail records (CDRs) from mobile phones in conjunction with open- and crowdsourced geospatial data, census records, and surveys. We bring together numerous existing and new algorithms to generate representative origin–destination matrices, route trips through road networks constructed using open and crowd-sourced data repositories, and perform analytics on the system’s output. We also present an online, interactive visualization platform to communicate these results to researchers, policy makers, and the public. We demonstrate the flexibility of this system by performing analyses on multiple cities around the globe. We hope this work will serve as unified and comprehensive guide to integrating new big data resources into customary transportation demand modeling.