Digital Twins in Public Bus Transport: Mapping the Road to Smarter Mobility

Imagine a live digital map of a city's bus system that shows where every vehicle is, how crowded each stop is, and where delays are likely to happen next. That is the promise of a "digital twin", a dynamic digital replica of a real-world system.

Researchers Manuel Andruccioli, Giovanni Delnevo, Roberto Girau, and Paola Salomoni from the Department of Computer Science and Engineering at Alma Mater Studiorum, Università di Bologna, have taken a close look at how this technology is being used in public bus transport. Their large-scale review of international research reveals a fast-growing field full of potential, but also marked by fragmentation and uneven development.

Digital twins are already common in manufacturing and energy systems. Now, cities are testing them in public transport, especially bus networks. Buses are complex to manage. They move through unpredictable traffic, depend on human behavior, and must meet rising sustainability goals. A digital twin can collect real-time data, simulate future scenarios, and help operators make smarter decisions before problems spiral out of control.

What Exactly Is Being Modeled?

The review analyzed 40 research studies from 16 countries. Together, these studies show that digital twins for buses focus on five main elements.

First, infrastructure. This includes bus stops, lanes, stations, and road layouts. These physical elements are the foundation of most systems because they are stable and easier to represent digitally.

Second, traffic flows and trips. Many digital twins simulate congestion patterns, travel times, and route performance. This allows cities to test changes virtually, such as adjusting traffic signals or relocating stops.

Third, passengers. Some systems analyze boarding patterns, waiting times, and crowd levels to better predict demand.

Fourth, the bus itself. A smaller group of studies models vehicle performance, including acceleration, braking, battery use, and energy consumption. This is especially important as cities shift toward electric buses.

Finally, fleet management. A few projects focus on how buses are assigned to routes, how charging is scheduled, and how fleets can run more efficiently.

Most digital twins combine several of these elements, but very few bring them all together in one fully integrated system.

The Technology Behind the Scenes

There is no single blueprint for building a digital twin. Researchers use a wide range of tools and system designs.

Many systems rely on client-server models, where data flows from buses and sensors to central servers. Others distribute computing across edge devices, local systems, and cloud platforms to handle real-time data more efficiently.

Simulation software such as SUMO and AnyLogic is often used to recreate traffic conditions. Visualization tools like Unity help build interactive dashboards or even 3D models. Python is the most common programming language because it works well for data analysis and machine learning.

Despite all this innovation, the field lacks standardization. Each project tends to be custom-built for a specific city or problem. This makes it harder to scale solutions or connect systems across regions.

Artificial Intelligence Adds Predictive Power

Nearly half of the reviewed studies use artificial intelligence or machine learning. These tools help predict passenger demand, travel times, energy use, and even mechanical faults.

For example, time-series models can forecast how many passengers will board at certain stops. Other algorithms estimate how much battery charge electric buses will need. Some systems detect unusual patterns that may signal technical problems.

However, AI is often used only for forecasting, not for automatic real-time control. Many projects rely on standard, ready-made models without deep testing or integration into larger decision systems. The technology is powerful, but still underused.

The Missing Human Factor

One of the most surprising findings is how little attention is paid to user experience. Only a small number of studies carefully examine how people interact with digital twins.

Most systems offer dashboards for transport operators, showing maps, charts, and performance indicators. A few include immersive 3D environments or virtual reality tools. But structured design processes and usability testing are rare.

This matters because even the most advanced system will fail if users find it confusing or hard to trust. Digital twins should support not only engineers and planners, but also potentially passengers and city leaders.

Promise and Challenges Ahead

Digital twins for bus transport show enormous potential. They can reduce congestion, improve energy efficiency, and help cities move toward cleaner mobility. They also allow planners to test ideas safely in a virtual environment before applying them in real life.

Yet the field is still maturing. There is no common architecture, no shared standards, and limited integration between AI, simulation, and user-centered design.

The next step, the researchers suggest, is to move from isolated prototypes to more holistic systems. That means clearer technical standards, better use of real-time AI, open data for transparency, and a stronger focus on human-centered design.

If cities succeed in combining technology with usability and trust, digital twins could become a central tool in shaping the future of sustainable public transport.