Skip to main content
ICTD 2025 Main banner
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Back

ICTD 2025

Data Sensing & Analytics

POSTER RECEPTION (View list of posters here)

Exploring 14 Years of Fresno Traffic Patterns: A Data-Driven Study Utilizing Machine Learning Models

Tuesday, June 10, 2025
4:45 PM – 6:00 PM MT

    Primary Author(s)

  • Pratham Aggarwal

    Undergraduate Student Assistant
    Fresno State Transportation Institute
    Fresno, CA, United States

    • Presenter(s)

  • Pratham Aggarwal

    Undergraduate Student Assistant
    Fresno State Transportation Institute
    Fresno, CA, United States

    • Co-Author(s)

  • RG

    Ritvik Gaur

    Graduate Research Assistant
    Fresno State Transportation Institute
    Fresno, CA, United States

    • Presenter(s)

  • RG

    Ritvik Gaur

    Graduate Research Assistant
    Fresno State Transportation Institute
    Fresno, CA, United States

    • Co-Author(s)

  • Aly M. Tawfik, PTP

    Associate Professor
    California State University, Fresno
    Fresno, CA, United States

    • Submitter(s)

  • Pratham Aggarwal

    Undergraduate Student Assistant
    Fresno State Transportation Institute
    Fresno, CA, United States

Abstract: This study delivers a comprehensive 15-year analysis (2008-2023) of traffic patterns in Fresno County, using extensive datasets from TomTom and Caltrans. We examine critical trends such as congestion build-up, peak-hour bottlenecks, temporal and seasonal variations, and variations in traffic speed dynamics along the city’s major routes and urban corridors. By leveraging advanced machine learning (ML) and artificial intelligence (AI), we extract key insights from this data and provide data-driven predictions for future traffic patterns and congestion trends.
A focal point of this research is the comparison of pre- and post-COVID-19 traffic patterns. Our analysis reveals shifts in traffic patterns, road usage, and overall congestion levels during and after the pandemic. These changes are visualized through graphical representations, highlighting the long-term impacts on regional traffic flows. Additionally, our AI models predict future congestion hotspots and provide actionable recommendations to help mitigate traffic challenges in the coming years.
The insights from this study equip transportation engineers, planners and policymakers with the tools needed to implement effective traffic management plans and design resilient infrastructures. By combining historical data analysis with AI-driven forecasts, this research offers a strategic framework for ensuring Fresno City’s transportation network is sustainable and future-ready.

Keywords: Traffic congestion, AI, machine learning, traffic forecasting, Fresno County, COVID-19, TomTom, Caltrans.

Learning Objectives:

Attendees can expect to learn the following from this session:
  • analyze 15 years of Fresno traffic data like average speed, sample size, etc. to identify trends like congestion, peak-hours, and seasonal variations for different avenues.
  • compare pre- and post-COVID-19 traffic patterns, identifying changes in avenue usage and congestion.
  • analyze future congestion trends and other trends predicted by utilizing advanced machine learning models.