Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Network-Level Travel Time Prediction Considering The Effects of Weather and Seasonality

Yufei Ai, Yao Yu, Wenjing Pu, Lu Gao, Yihao Ren

TL;DR

This study proposes a framework for predicting network-level travel time index (TTI) using machine learning models and shows that the ridge regression model outperformed the other models in both short-term and long-term predictions.

Abstract

Accurately predicting travel time information can be helpful for travelers. This study proposes a framework for predicting network-level travel time index (TTI) using machine learning models. A case study was performed on more than 50,000 TTI data collected from the Washington DC area over 6 years. The proposed approach is also able to identify the effects of weather and seasonality. The performances of the machine learning models were assessed and compared with each other. It was shown that the ridge regression model outperformed the other models in both short-term and long-term predictions.

Network-Level Travel Time Prediction Considering The Effects of Weather and Seasonality

TL;DR

This study proposes a framework for predicting network-level travel time index (TTI) using machine learning models and shows that the ridge regression model outperformed the other models in both short-term and long-term predictions.

Abstract

Accurately predicting travel time information can be helpful for travelers. This study proposes a framework for predicting network-level travel time index (TTI) using machine learning models. A case study was performed on more than 50,000 TTI data collected from the Washington DC area over 6 years. The proposed approach is also able to identify the effects of weather and seasonality. The performances of the machine learning models were assessed and compared with each other. It was shown that the ridge regression model outperformed the other models in both short-term and long-term predictions.
Paper Structure (11 sections, 1 equation, 5 figures, 2 tables)

This paper contains 11 sections, 1 equation, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Real-Time Prediction
  3. Short-Term Prediction
  4. Long-Term Prediction
  5. Existing Research on Seasonality and Weather
  6. Case Study
  7. Descriptive Statistics
  8. Model evaluation criterion
  9. Feature selection
  10. Model Comparison
  11. CONCLUSION

Figures (5)

  • Figure 1: Daily Travel Time Index from 1/1/2010 to 1/31/2016
  • Figure 2: Averaged Travel Time Index as a Function of Month
  • Figure 3: Averaged Travel Time Index over Time of a Day
  • Figure 4: Averaged Travel Time Index per Weekday
  • Figure 5: Averaged Travel Time Index per Year