Digital Twins: the key to tomorrow’s transport infrastructure management?

With recent technological advances, digital twins (DTs) are becoming increasingly beneficial in the development and management of transport infrastructure.

As virtual representations of products, processes and facilities, DTs are powerful frameworks capable of interacting with real-time data, enabling the design, simulation and operation of the real-world structures to which they correspond. “Compared to traditional transportation infrastructure management technologies, DT technology offers advantages such as real-time capabilities, digitization, and proactive features, enabling more efficient optimization of transportation system operations and bringing positive impacts to national economic and environmental sustainability,” explains a review of current applications, challenges and future directions for DTs, published in February 2025 by researchers at China’s Shenzhen University (SU).

The review highlights several global case studies that demonstrate how DT technology is being adopted to address specific transportation challenges, as well as their versatility and efficacy within this context.

Simulating urban development scenarios

Singapore’s comprehensive DT “incorporates real-time data from its road networks, public transit systems, and environmental sensors” to simulate “various urban development scenarios, aiding decision-making in road network configuration, public transit enhancements, and traffic congestion mitigation”. The review says the DT’s successful implementation showcases its potential to foster more efficient, sustainable and responsive urban environments.

Germany’s DT technology achieves exceptionally detailed simulation accuracy, extending to the real-time perception of car air-conditioning and wheel wear. The review notes that implementation has begun on a new DT train set: “Rail transport logistics systems have developed a geographic information systems (GIS) for DTs, using a qualitative explorative design to establish a validated strategy.”

This strategy, it says, emphasises a socio-technical system focus, enabling user-oriented development and accounting for complex conditions, while the technology aims to optimise operations and intelligently manage rail transport assets.

Integrated transport management within a wider national context

In the UK, DT strategies are supported at a national level by initiatives like the National Digital Twin Programme, which aims to facilitate connected DTs across different sectors, including transportation. “DT technology is employed primarily in three areas: alleviating road congestion, managing motorway projects, and enhancing real-time traffic and travel information systems,” reports the review.

“As a leading city-level example, Transport for London (TfL) utilizes a DT to oversee traffic and public transport in real time. By integrating data from numerous sensors, cameras, and public transport networks, the DT facilitates dynamic traffic signal adjustments, congestion tracking, and incident management.” This integrated approach has significantly decreased traffic delays and enhanced public transport reliability, with the review noting: “London’s case demonstrates how a city can pilot and refine DT solutions within a broader national policy context.”

Proactive monitoring of essential infrastructure

In China, DTs are being used to monitor the health of essential infrastructure like bridges and tunnels. “By employing sensor data and predictive analytics, these DTs detect structural issues early, enabling prompt maintenance and extending the assets’ service life,” says the review, adding that this proactive strategy has proven more cost-effective and safer than conventional maintenance methods.

It highlights work done by the East China Survey and Design Institute of China Electronics Chamber of Commerce (CECC), which has developed a next-generation integrated management system for the entire lifecycle of building information modeling (BIM) in rail transit engineering, leveraging technologies such as BIM, GIS, Internet of Things (IoT), artificial intelligence (AI) and cloud computing.

“This system enhances visibility and ensures the seamless flow of information across the design, construction, operation, and maintenance phases, alongside intelligent perception, analysis, and decision-making,” the review elaborates.

Deep learning for dynamic testing and assessments

Australia’s Curtin University has introduced a 3D dynamic displacement measurement technique. Its binocular camera system without targets allows for full-field measurement of civil engineering structures’ dynamic displacements. 

“It has also formulated several deep-learning-based structural damage identification methods, enhancing identification accuracy,” says the review. “These innovations have been successfully applied in the dynamic testing, modal identification, condition assessment, and comfort evaluation of significant projects like the large-scale pedestrian bridge in Matagarup and the long-term monitoring and performance evaluation of the Rockingham Freeway Bridge.”

Enhancing real-time traffic management and asset maintenance

In the US, state transport departments are piloting DTs to enhance real-time traffic management and asset maintenance. California’s I-210 Pilot integrates DT-driven insights from sensor data, connected vehicle inputs and traffic signals to reduce congestion through adaptive control, and improve safety, incident response and operational efficiency. 

Colorado’s I-70 corridor project, meanwhile, combines continuous sensor data with AI-based traffic predictions and cloud analytics to optimise real-time traffic flow. “These initiatives aim to streamline congestion management and enable predictive maintenance for highway infrastructure, contributing to cost-effective and resilient transportation networks,” the review explains. Furthermore, “The US Federal Highway Administration collaborates with research institutions on DT studies, reflecting a growing interest in leveraging DTs for nationwide infrastructure modernization.”

Optimising maritime traffic and multimodal coordination

The Netherlands, renowned for its advanced logistics and water management, has deployed a DT at the Port of Rotterdam to optimise maritime traffic and multimodal coordination. “Real-time data from ships, road transport, and rail systems are integrated into a unified DT platform for route optimization and congestion reduction,” the review says. “Additionally, Dutch authorities are exploring national-level, cross-sector DT strategies that integrate water management, energy, and transportation infrastructure to enable holistic planning and operational efficiency.”

SA DTs to support railway infrastructure management?

A 2023 Stellenbosch University study presents a concept and case study implementation for a system of DTs to support railway infrastructure maintenance management, using a subset of the railway infrastructure managed by the Passenger Rail Agency of South Africa (PRASA) as the physical asset. “The DT system can acquire and integrate data from diverse data sources and be adapted to a changing context (in terms of user requirements, infrastructural elements, and data sources),” say the researchers, emphasising the DT’s scalability and “potential for larger implementations, within and beyond PRASA”, and its potential to support data-led railway infrastructure maintenance decisions.

Challenges and future potential

“The technical challenges of integrating different DT systems remain unclear, which to some extent limits the potential of DT technology in the management of transportation infrastructure,” caution the SU researchers. System and technical challenges, they say, include issues related to data quality and integration, real-time processing requirements, sustaining model accuracy and ensuring system interoperability: “Addressing these challenges is critical to unlocking the full potential of DTs throughout the entire lifecycle of transportation infrastructure, from planning and design to operation, maintenance, and decommissioning.”

Certain advances are helping with this: advanced data processing techniques like machine learning (ML) algorithms to filter noise and detect errors in real-time data streams; edge computing that processes data locally at the source as a potential solution to real-time processing requirements; and the dynamic incorporation of non-destructive testing (NDT) data to enhance the fidelity of digital replicas and facilitate proactive, precision-targeted interventions.

The researchers see the integration of advanced analytics, particularly AI and ML, as a promising future direction for transport DTs, explaining: “While current DT frameworks primarily focus on real-time monitoring and basic predictive modeling, future systems could leverage advanced analytics to provide deeper insights and optimize transportation networks throughout their entire lifecycle.”

Standardisation will be a critical enabler for widespread DT adoption across the transport infrastructure lifecycle. “The lack of standardized frameworks for data exchange, modeling methods, and communication protocols poses significant challenges,” the review cautions, suggesting a centralised transportation infrastructure data repository as a shared resource for DT systems to further enhance interoperability. 

It also stresses the imperatives of equitable access to transportation services and clear policies and guidelines on data privacy, usage and security for DT applications across all lifecycle stages. This will “require collaboration among stakeholders to address the diversity of technologies involved.”

Digital twins will clearly play a pivotal role in managing tomorrow’s transport infrastructure. As their effectiveness and cross-sector applicability are enhanced, the sky is the limit. However, decision-makers will need to ensure robust policy frameworks and the necessary checks and balances to overcome diverse challenges, as well as avoid privacy issues and cybersecurity-related concerns inherent in connected technology.