Multiple Uses of Big Data for Model Validation and Express Lanes Traffic Forecasts

Amar Sarvepalli

2 citations0/0 files storedTransportation Research Record Journal of the Transportation Research Board

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Transportation Planning and Optimization Traffic control and management Traffic Prediction and Management Techniques

Abstract

This paper highlights a variety of uses for Big Data when developing project forecasts and model validations. In most travel models, validation often refers to estimating model volumes close to the observed highway counts. While this is an established practice for producing reasonable confidence in the model, these statistics are often not sufficient to build confidence in the project forecast. This is especially true for investment-grade level traffic and revenue forecasts for projects involving congestion pricing. This paper explores the application of Big Data to validate subarea models in multiple dimensions: subarea district-to-district origin-destination (O-D) flows; corridor segment-to-segment O-D flows; and trip length distribution by O-D types for the I-4 Ultimate Express Lanes Study. Additionally, the paper reviews historical O-D flows to determine the peak seasonal flow and appropriate O-D data to use in model validation and seed tables for Origin-Destination Matrix Estimation (ODME). In addition to model validation, the expanded Big Data O-D trips were assigned to multiple paths for each O-D pair built via Google Directions API to study the eligible corridor trips and the alternative corridors competing with the project. Furthermore, spatiotemporal distributions from Big Data were used to develop time-dependent trip tables for the Dynamic Traffic Assignment (DTA) model. Several international tourist attractions located along the I-4 Ultimate Corridor serve high visitor and weekend traffic, and Big Data was used to analyze and develop a weekend distribution model. Each of these modules involves some form of observed data, all coming from one source, “Big Data.”

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 2 citations exist upstream.

References

1997An introduction to error analysis: the study of uncertainties in physical measurements 2012Understanding individual mobility patterns from urban sensing data: A mobile phone trace example 2015Origin–destination trips by purpose and time of day inferred from mobile phone data 2016The promises of big data and small data for travel behavior (aka human mobility) analysis 2002The propagation of uncertainty through travel demand models: An exploratory analysis 2014Big Data: A Big Mistake?2012Are call detail records biased for sampling human mobility?2017Origin-Destination Trip Matrix Development: Conventional Methods versus Mobile Phone Data

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.