Traffic management policies: experiences from Istanbul and Buenos Aires

Istanbul and Buenos Aires combat traffic congestion via AI, smart systems, and infrastructure upgrades, slashing accidents and delays.

In February 2025, the UNDP’s SDG Local Solutions series focused on how cities can prevent traffic accidents through innovative policies and technological solutions. Two cities, Istanbul, Türkiye, and Buenos Aires, Argentina, shared their experiences in addressing the challenges, solutions, and lessons learned to improve urban mobility, road safety and prevent accidents to happen.

Traffic accidents have an impact on lives and economies. This article highlights different approaches to traffic management and provide recommendations for other cities seeking to implement similar policies.

The video recording can be watched on our YouTube channel – also available in Spanish and French.

Istanbul Challenges

Istanbul, Türkiye’s largest city and one of Europe’s most populated urban centers, faces severe traffic congestion. With a population of 20 million (including tourists), the city experiences approximately 34 million daily trips, with 7 million vehicles on its roads and 2 million intercontinental trips between Asia and Europe. The city’s complex transportation system and high vehicle density make traffic management a critical issue. Key challenges include:

High accident rates due to congestion and human errors.

Inefficient traffic flow, leading to extended commute times.

Challenges in funding extensive transportation infrastructure.

Solutions implemented

Smart traffic management system

The Istanbul Metropolitan Municipality Traffic Directorate has implemented an intelligent transport system that includes real-time traffic monitoring using sensors, cameras and meteorological data.

Traffic density maps and floating car data are utilized to optimize routes and manage congestion.

Artificial intelligence for traffic optimization

AI-driven accident prediction models have been developed using machine learning to identify high-risk areas, allowing preventive measures to be taken before accidents occur.

AI-based smart intersections adjust traffic signals dynamically, improving traffic flow and reducing delays.

Real-time public communication and enforcement

The city provides real-time traffic updates through a dedicated mobile application, social media, and electronic road signs to inform drivers of congestion, accidents, and alternative routes.

Istanbul has implemented mobile and fixed electronic traffic enforcement systems, detecting violations such as red-light running, overspeeding, and wrong-way driving.

Infrastructure improvements and sustainable mobility

The city has expanded pedestrian zones and bike lanes to promote safer non-motorized transportation.

Results achieved

95% reduction in response time for traffic incidents.

A significant reduction in congestion on major roads, improving average travel time.

Enhanced response times to accidents due to real-time monitoring and AI-driven risk assessment.

Decreased accident frequency in high-risk intersections after the implementation of AI-based traffic signal optimization.

Buenos Aires

Challenges

Buenos Aires, Argentina’s capital, faces similar traffic management issues, with approximately 10,000 traffic incidents reported annually. The primary challenge for city officials was data collection and analysis, as the traditional manual classification process for road incidents was time-consuming and inefficient. Other key issues included:

High reliance on human data classification, causing delays in policy implementation.

Need for improved road infrastructure and enforcement to enhance road safety.

Public resistance to new road safety infrastructure (bike lanes, speed controls)

Solutions implemented

Artificial intelligence for incident classification

Buenos Aires implemented an AI-driven system to automate the classification of traffic incidents based on police reports.

The system reads and categorizes accident reports, identifying key details such as the type of accident, involved parties, and severity of injuries.

Automated data processing and predictive analytics

AI technology reduced the time required for data processing from 480 hours to just 24 hours per year.

The system ensures high accuracy, maintaining classification quality above 94% while significantly cutting operational costs.

Machine learning models analyze historical accident data to predict high-risk zones, allowing preventive measures to be implemented.

Integration with healthcare and emergency response systems

Plans are in place to integrate AI tools with hospital records to assess injury severity and enhance response strategies.

Real-time traffic data is used to optimize ambulance and emergency response times.

Infrastructure and behavioral interventions

Buenos Aires has implemented dedicated bus lanes to improve public transport efficiency and reduce congestion.

Physical barriers and redesigned intersections have been installed to encourage safer driving speeds and pedestrian movement.

Awareness campaigns educate the public on the risks of speeding and reckless driving, supported by increased traffic enforcement.

Results achieved

95% reduction in data processing time, enabling faster decision-making.

97% reduction in operational costs associated with data classification.

Enhanced accuracy in identifying high-risk zones, leading to targeted interventions.

Lessons learned

Data is essential for effective traffic management

Both cities highlight the importance of collecting and analyzing real-time and historical data to improve road safety.

Governments can invest in AI-driven solutions to enhance data processing and decision-making capabilities.

Public communication enhances traffic safety

Istanbul’s real-time updates and Buenos Aires’ transparent reporting mechanisms have improved public awareness and compliance with traffic regulations.

Cities can develop mobile applications, traffic dashboards, and social media engagement strategies to keep residents informed.

AI and automation reduce human error

Automated data processing enhances efficiency in identifying traffic patterns and hazards.

Cities can explore machine learning models for traffic forecasting, risk assessments, and dynamic signal control to optimize urban mobility.

Infrastructure investments

Physical interventions such as smart intersections, traffic signals, and pedestrian-friendly urban designs reduce accidents and improve mobility.

Cities can allocate resources for road redesign and public transportation enhancements.

Sustainable and active mobility can be encouraged

Expanding bicycle lanes and pedestrian zones can contribute to safer and more sustainable urban mobility.

Public policies can prioritize non-motorized transportation options to decrease reliance on private vehicles.

Conclusion

The case studies of Istanbul and Buenos Aires demonstrate that technology, smart traffic management, and real-time data can significantly improve urban mobility and safety. AI can help identify accident-prone areas and optimize traffic flow. Additionally, strong communication and infrastructure investments are essential for safer urban environments. Other cities can draw lessons from these examples by adopting data-driven strategies, using AI tools, and prioritizing sustainable mobility. 

Pic:pixabay