National Academies Press: OpenBook
« Previous: Front Matter
Page 1
Suggested Citation:"Chapter 1 - Introduction." National Academies of Sciences, Engineering, and Medicine. 2023. Application of Big Data Approaches for Traffic Incident Management. Washington, DC: The National Academies Press. doi: 10.17226/27300.
×
Page 1
Page 2
Suggested Citation:"Chapter 1 - Introduction." National Academies of Sciences, Engineering, and Medicine. 2023. Application of Big Data Approaches for Traffic Incident Management. Washington, DC: The National Academies Press. doi: 10.17226/27300.
×
Page 2
Page 3
Suggested Citation:"Chapter 1 - Introduction." National Academies of Sciences, Engineering, and Medicine. 2023. Application of Big Data Approaches for Traffic Incident Management. Washington, DC: The National Academies Press. doi: 10.17226/27300.
×
Page 3

Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.

1   Advances in the practice of Traffic Incident Management (TIM) continue to improve the safety of responders and the traveling public, the reliability of individual travel and the movement of goods, and the time required to mitigate traffic incidents. These advances have manifested through technologies such as unmanned aircraft systems for crash reconstruction; the use of crowdsourced data for localized app-based traveler information; and geofenced, emergency two-way communication with travelers stranded in major incidents. These technologies also generate data that can be mined and integrated with traditional TIM data—such as data from traffic management centers (TMCs), safety service patrols (SSPs), state crash reports, and computer-aided dispatch (CAD) systems—to make marked improvements in planning for and conducting TIM. Combining these data with further data integration with work zone, road weather, and maintenance programs—as well as other third-party data, such as automatic vehicle location (AVL) and connected vehicles (CVs)—could further improve TIM on freeway facilities and expand TIM beyond freeway facilities. This integration could help realize the goals of proactive and predictive transportation systems management and operations. Data represent a tremendous asset for every agency, and one that is likely to be underutilized by most agencies. Transportation agencies are increasingly recognizing that there is vast potential in their data, as well as data from partner organizations, third parties, and emerging technologies. Agencies also face a host of challenges to use data in new ways, particularly for the application of big data, which prevents them from harnessing the data to improve decision-making at the enterprise, program, and operator levels. The term “big data” represents much more than “a lot of data.” “Big data” refers to not only the volume or amount of data available, but also the speed at which the data are available, the variety or diversity of datasets available, the veracity or trustworthiness of the data, and the value that data bring to an organization. More importantly, big data represent a fundamental change in how data are collected, managed, analyzed, and used by organizations, both to support real-time operations and to uncover important trends and relationships that could improve transportation operations and safety. NCHRP Project 17-75, “Leveraging Big Data to Improve Traffic Incident Management,” provided the first research opportunity to focus specifically on the application of big data approaches for TIM, and the final research report—NCHRP Research Report 904: Leveraging Big Data to Improve Traffic Incident Management (Pecheux, Pecheux, & Carrick, 2019)—presents guidelines to move transportation agencies toward the implementation of big data for TIM. The report illuminates how the big data approach differs from traditional data management and offers big data opportu- nities for improving TIM that traditional techniques simply cannot accomplish. The report also C H A P T E R   1 Introduction

2 Application of Big Data Approaches for Traffic Incident Management emphasizes that applying the big data approach to TIM will not be a trivial task given the gaps in data, technical, and institutional readiness: • Data readiness. Traffic incidents are infrequent events in the context of big data—thousands of traffic incident records per year versus “typical” big data records of thousands per minute. With traffic incident data alone, the big data approach would require data over a vast geographic expanse to detect significant trends and relationships. Moreover, targeted processing to correct for gaps in completeness, quality, and resolution is required when integrating a variety of data to support TIM use cases. Agencies also encounter challenges to data accessibility and availability. • Technical readiness. Transportation agencies currently lack the skills required to establish a big data environment, understand the implications of a varied suite of technology stacks, apply agile approaches, and improve user experience. To implement a big data approach, agencies need to develop essential competencies to understand and procure technical support, at the very least. • Institutional readiness. Transportation agency culture is not conducive to the fundamental changes that will be necessary to implement big data for TIM and other applications, as evi- denced by data silos and a fear of discovering data imperfections. Another challenge lies in the complex relationship between Information Technology (IT) and transportation groups— centered around policies and regulations—which makes the use of cloud services and new software or platforms a problematic endeavor. Indeed, the data governance and management approaches at most transportation agencies are inherently contrary to the big data approach and, by design, present obstacles to implementing big data. More importantly, agencies need to support their workforce to evolve and become more open to change. This change will affect what they do, how they do it, what resources they use, and the pace of decision-making. These data, technical, and institutional readiness gaps challenge transportation agencies to use data in new and innovative ways, as evidenced by the following examples: • Agencies struggle to effectively apply new types of crowdsourced data for TIM. • Big data efforts in transportation under the umbrella of machine learning (ML) and artificial intelligence (AI) often fall flat. For example, discussions with one agency that procured a tech- nology for predictive TIM confirmed that the technology’s predictions of incidents do not yet meet the accuracy of TMC operators with just a few months of experience. • Efforts to quantify the severity and frequency of secondary crashes and link these to specific TIM practices, such as responder training, have proved challenging. • SSP routes, coverage, and frequency are evaluated infrequently, often once every few years, due to data constraints and institutional practices. 1.1 Research Objectives NCHRP Research Report 1071: Application of Big Data Approaches for Traffic Incident Man- agement details the research conducted for NCHRP Project 03-138, “Application of Big Data Approaches for Traffic Incident Management (TIM).” This report seeks to demonstrate the appli- cation of guidelines presented in NCHRP Research Report 904; to demonstrate the feasibility and value of the big data approach for TIM among transportation and other responder agencies; and to document application challenges, along with tools and techniques to overcome these challenges. The research objectives of NCHRP Project 03-138 included the following: • Demonstrate the feasibility and practical value of big data approaches to improve TIM; and • Provide guidelines, including techniques and tools, to address the findings and recommen- dations of NCHRP Research Report 904. These objectives were accomplished through the following activities: • Conducting interviews with 11 transportation agency TIM programs to identify pain points, • Developing a list of potential TIM big data use cases to address the pain points,

Introduction 3 • Performing a comprehensive assessment of traditional and big data sources relevant to the use cases, • Establishing big data pipelines for the selected use cases, • Developing case studies to describe each of the big data use cases and pipelines, and • Creating guidelines that expand and refine the guidelines presented in NCHRP Research Report 904. 1.2 Organization of Report The rest of the report is organized as follows: • Chapter 2: Gather Information and Data and Define Use Cases. This chapter describes the approach, findings, and outputs of information gathered from transportation agencies and data providers via interviews with TIM programs, the selection of TIM big data use cases, and the associated data collection. • Chapter 3: Datasets and Data Quality. This chapter presents the results of the assessment of 16 data sources relevant to the identified use cases. The results are presented in terms of six dimensions of data quality: timeliness, completeness, accuracy, conformity, consistency, and integrability. An overview of each data source is provided, followed by a summary of the chal- lenges, limitations, and associated recommendations. • Chapter 4: TIM Big Data Use Cases. This chapter presents and discusses case studies associ- ated with the four use cases/data pipelines developed to demonstrate the feasibility and value of the big data approach for improving TIM. Each case study provides an overview of the use case, the datasets leveraged, a description of the data pipeline, the associated data analysis/ products, lessons learned, and recommendations for implementation. • Chapter 5: Estimated Costs of Cloud Environments and Data Pipelines. This chapter presents estimated average cost ranges for the data pipelines developed for NCHRP Project 03-138. These ranges are based on the understanding that the cloud provides flexibility and scalability and can fluctuate month to month based on data storage, cloud processing/queries, and so on. Costs are estimated by use case/data pipeline and are broken down by data storage (e.g., archival storage, real-time curated-data storage) and data query and analytics (e.g., data ingestion and processing, real-time curated data). • Chapter 6: TIM Big Data Guidelines. This chapter presents guidelines for transportation agencies and TIM programs regarding the development and implementation of TIM big data pipelines. The guidelines build from, enhance, and refine the big data guidelines presented in NCHRP Research Report 904; pull from big data/modern data management guidelines pre- sented in NCHRP Research Report 952: Guidebook for Managing Data from Emerging Tech- nologies for Transportation (Pecheux, Pecheux, Ledbetter, & Lambert, 2020); and include recommendations, techniques, and “tips” specific to developing the TIM big data pipelines in this project. The guidelines are presented across six categories: data acquisition and quality; data environment, platform, and architecture; data management; data processing, tools, and mining techniques; data pipeline development and operations costs; and data sharing. • Chapter 7: Conclusions and Recommendations. This chapter provides conclusions drawn from the research effort and offers potential next steps and recommended research. There are 16 supplemental appendices with detailed findings from the assessment of 16 tra- ditional and big data sources relevant to the selected TIM use cases, as described and referenced in Chapter 3, available on the National Academies Press website (nap.nationalacademies.org) by searching for NCHRP Research Report 1071: Application of Big Data Approaches for Traffic Incident Management.

Next: Chapter 2 - Gather Information and Data and Define Use Cases »
Application of Big Data Approaches for Traffic Incident Management Get This Book
×
 Application of Big Data Approaches for Traffic Incident Management
MyNAP members save 10% online.
Login or Register to save!
Download Free PDF

Big data is evolving and maturing rapidly, and much attention has been focused on the opportunities that big data may provide state departments of transportation (DOTs) in managing their transportation networks. Using big data could help state and local transportation officials achieve system reliability and safety goals, among others. However, challenges for DOTs include how to use the data and in what situations, such as how and when to access data, identify staff resources to prepare and maintain data, or integrate data into existing or new tools for analysis.

NCHRP Research Report 1071: Application of Big Data Approaches for Traffic Incident Management, from TRB's National Cooperative Highway Research Program, applies the guidelines presented in NCHRP Research Report 904: Leveraging Big Data to Improve Traffic Incident Management to validate the feasibility and value of the big data approach for Traffic Incident Management (TIM) among transportation and other responder agencies.

Supplemental to the report are Appendix A through Appendix P, which detail findings from traditional and big data sources for the TIM use cases; a PowerPoint presentation of the research results; and an Implementation Memo.

READ FREE ONLINE

  1. ×

    Welcome to OpenBook!

    You're looking at OpenBook, NAP.edu's online reading room since 1999. Based on feedback from you, our users, we've made some improvements that make it easier than ever to read thousands of publications on our website.

    Do you want to take a quick tour of the OpenBook's features?

    No Thanks Take a Tour »
  2. ×

    Show this book's table of contents, where you can jump to any chapter by name.

    « Back Next »
  3. ×

    ...or use these buttons to go back to the previous chapter or skip to the next one.

    « Back Next »
  4. ×

    Jump up to the previous page or down to the next one. Also, you can type in a page number and press Enter to go directly to that page in the book.

    « Back Next »
  5. ×

    To search the entire text of this book, type in your search term here and press Enter.

    « Back Next »
  6. ×

    Share a link to this book page on your preferred social network or via email.

    « Back Next »
  7. ×

    View our suggested citation for this chapter.

    « Back Next »
  8. ×

    Ready to take your reading offline? Click here to buy this book in print or download it as a free PDF, if available.

    « Back Next »
Stay Connected!