Leveraging innovative technologies to reduce congestion in cities

Advancements in AI, data analytics and predictive modeling can streamline urban mobility

By Dr. Babu K. Veeregowda, PE, PTOE | HNTB

Cities across the country are seeking innovative ways to improve mobility and reduce congestion — reshaping how goods move, how people connect and how communities grow.

Technologies such as artificial intelligence (AI), machine learning, predictive modeling, and real-time data analytics are redefining what’s possible in traffic management. These tools enable agencies to anticipate congestion before it occurs, optimize traffic flow in real time and enhance safety for all users.

When combined with human-centered mobility and thoughtful design, these tools can help create systems that not only ease congestion but also enhance public trust and advance broader goals.

Turning data into real-time decisions

AI-driven analytics redefine traffic management by transforming vast amounts of real-time data into actionable insights. By leveraging connected vehicle technology, sensor networks and predictive algorithms, agencies can create adaptive systems that anticipate conditions and respond dynamically as they unfold.

AI-powered traffic simulation models make it possible to test and refine strategies before deployment, minimizing disruptions and improving operational confidence. Predictive modeling enables agencies to visualize where congestion is likely to build and take preventive action, turning data into foresight that enhances safety, reliability and traveler experience.

Across the industry, these capabilities are beginning to show measurable results:

Machine learning-based traffic forecasting: AI algorithms analyze historical and real-time congestion patterns to predict and mitigate traffic bottlenecks before they occur.
Transit signal priority for emergency response and events: AI optimizes transit preemption for large-scale events such as the FIFA World Cup, the Olympics and the Super Bowl — balancing roadway capacity with public transit flow.
Dynamic toll pricing: AI assesses traffic congestion levels to adjust toll prices in real time, encouraging balanced roadway use and reducing overall delays.

Balancing technology with human insight

While AI and data analytics provide powerful tools for congestion mitigation, transportation systems function best when human intuition and experience guide how those tools are applied. Technology can analyze patterns and predict outcomes, but people can remove bias, correct for flawed or incomplete datasets and bring the contextual understanding needed to transform these insights into meaningful outcomes.

For example, driver and commuter behaviors often shift in response to new congestion policies, roadway changes or the introduction of a new transit service. Engineers and planners play a critical role in monitoring those behaviors and recalibrating AI models to ensure they continue to reflect real-world conditions.

Equally important is maintaining a holistic view of urban mobility. AI-driven systems are most effective when they account for all modes of travel — not only vehicles, but also pedestrians, cyclists and transit riders. When technology and human judgment work together, agencies can create integrated mobility networks that enhance safety, improve flow and deliver more equitable outcomes for every traveler.

Building readiness for responsible AI in mobility

As cities adopt AI-driven traffic management, thoughtful implementation is essential to ensure these tools deliver equitable, secure and lasting benefits. Achieving that balance requires both strategic planning and proactive safeguards.

Transparent and equitable data practices: Agencies can strengthen trust by validating datasets and training AI models with equity in mind — ensuring predictions and outcomes reflect the needs of all communities.

Privacy and security safeguards: Embedding strong privacy protections and cybersecurity measures prevents excessive tracking, protects systems against potential manipulation and provides users with trust that personal information will not be used.

Collaboration and continuous improvement: Partnerships among government agencies, universities and technology providers enable cities to refine and test AI-based strategies through pilot programs before broad deployment. Regular model updates ensure systems evolve with changing travel behaviors and infrastructure. Data sharing amongst regional, national and international agencies spread best practices and lessons learned.

Ethical and inclusive deployment: When implemented with transparency and community engagement, AI-powered mobility can reduce congestion while advancing access and opportunity across the transportation network.

Smart Signal Optimization: AI-driven signal optimization continuously analyzes traffic flow data and adjust signal timings accordingly, reducing congestion, increasing intersection throughput and improving safety for pedestrians and cyclists alike.

NCTA

Case Study: AI in action

East Side Coastal Resiliency Project

StreetLight data was harnessed to analyze millions of data points, enabling planners to model traffic flow and coordinate the first-ever 10-hour closure of the FDR Drive. RapidMiner validated projections and informed mitigation strategies. This fusion of data science and engineering set a new benchmark for urban infrastructure planning — reducing congestion, minimizing disruption and enhancing safety.