Today, over 50% of the global population lives in urban centers, and this proportion is projected to climb to 66% by 2050. This population surge will predominately occur in developing countries with poor infrastructure, where cities already struggle to meet their inhabitants’ mobility needs. The next 30 years will challenge their existing road network, public transportation systems, and emergency response strategies. It is critical for authorities to anticipate this urban growth and redesign their current infrastructure to ensure the sustainable development of their cities.

Sustainable urban development depends on accurate mobility predictions to design infrastructure and organize emergency responses. In developing countries, it is difficult to gather the data necessary to set a successful urban planning agenda. Generally, the only data available to map commutes come from census or surveys, which have several limitations:

• Surveys are conducted every five to ten years, so census data can be up to a decade old.
• Surveys are expensive to conduct and prone to errors.
• Surveys rely on small samples which are often not representative of the entire population.

Furthermore, traditional traffic data collection requires specific infrastructure or staff that are unavailable or too costly for cities in LDCs. As a result, urban planners have a very limited oversight on the mobility issues of a city.

To help urban planners and city officials make better policy decisions, UNCDF, in collaboration with Dalberg Data Insights and the Kampala Capital City Authority (KCCA) analyzed telecom and traffic sensor data to map commuter travel patterns: origin-destination trips and average trip durations. Access to up to date information allows planners to make better informed decisions.

Transport Mobility Application

In response to the need for sustainable urbanization the Transport Mobility Application was developed as a solution to analyze and predict mobility patterns in fast growing cities like Kampala. By anonymizing and aggregating the mobile phone transactions of millions of people, we can understand where people live, work, and how they commute from A to B. With this information, we can then map the most popular routes and the areas of congestion.

The first version was co-designed with ROM Transportation Engineering, an urban planning consultant firm, and the Kampala Capital City Authority to support the Transportation Master Plan for Greater Kampala Metropolitan Area. The application measured the average mobility patterns in and around the city of Kampala for different time periods in the day and in the week.

The tools provide crucial insights for the optimization of the transportation network in the country such as:

• Origin-Destination Flows: How many trips (inbound and outbound) is a specific neighborhood generating over time? Which destination attracts the most people? From which place are the most people departing?
• Travel Path Estimation: What is the origin neighborhood of inbound trips and what is the destination neighborhood of outbound trips? What are the most popular commuting trips?
• Travel Time Estimation: What is the average travel time between two neighborhoods?
• Distribution Flow: How are the commuters spread over time between two areas?

Real-time information

Dalberg Data Insight’s innovative approach to mobility data unlocks the potential for intelligent city planning and urbanization. In comparison to traditional data sources, the Mobility Analytics Manager has important advantages:

• The data is graphic, processed, and stabilized, giving more information to planners than they previously had
• The data is comprehensive, accurate, real-time, as opposed to a traditional manual data collected every 5 to 10 years
• The tools allow officials to interact with the data and visualize mobility flows across specific areas over time

By providing accurate insights into the mobility patterns of a population, users of the transport mobility application can make decisions about a city’s design and respond to the population’s exact needs more accurately. Such, were to install traffic lights.