Case studies

The LeMO project performs seven case studies in transport related areas through the course of this project. These case studies will involve organisations actively using big data for specific purposes and enable LeMO to understand strategies, actions and changes in behaviour associated with big data and identify their resultant merits and demerits. These case studies will produce evidence-based, clear and precise questions based on rigorous knowledge that illuminate opportunities, problems and viable solutions to be further investigated in the LeMO roadmap. The identification of these issues will be complemented by a horizontal analysis to identify challenges, opportunities, limitations and other consequences of cross-disciplinary nature, and thus relevant to big data in transport sector.


Rail transport data

Research on rail transport refers to all land-bound passenger and freight transport on dual and single fixed rail, including heavy rail, light rail, tram, metro, funicular and monorail.
Types of data that this case study offers include passenger, rail network, freight and logistical data. Issues that will be addressed include innovation in infrastructure, efficiency in transport routes, resource management and supply chain, environmental impacts, vulnerability in potential crisis and data protection.


Open data and the transport sector

Open data is the idea that data should be freely available to everyone to use as they wish. Open data supports and enhances big data’s availability and potential. It is already changing the way the governments address issues domestically and internationally. Moreover, open data becomes actionable intelligence, which could provide an economic boost and increased job creation. The case study will explore issues such as enabling ‘mass mobilisers’ to disseminate and make data understandable by the general public, not just data scientists. Presenting the data in a way that makes it accessible to all users, especially the public, which is often left behind in the availability and agency to use the data.


Real-time traffic management

Big data allows warnings ahead of traffic jams, lane handling, traffic flow predictions, etc. Going from big data to active traffic management requires merging big data with data from fixed sources. The use of archived data allows improving individual route planning, to measure bottlenecks and delays, to measure system reliability, to determine priorities for infrastructure improvement, and to analyse the impact of the investments made. Social media play a key role in transport with continuous, inbound information (stimulus to traffic control) and outbound information (stimulus to road user). Moreover, without accurate demand estimation, it is difficult for transport operators to provide their services and make other important traffic management decisions. In this case study, we will discuss a methodology to estimate passenger demand for public transport services using social media and mobile phone data. 

Logistics and consumer preferences

The success or failure of freight transport measures fundamentally depends on local policy makers’ knowledge and awareness of stakeholders’ preferences. The behavioural approach calls for stakeholder-specific big data acquisition and model estimation. Considering the cost and time to perform an appropriate big data acquisition process and the ever-present aim of compressing research costs, it is important to investigate innovative big data acquisition procedures that can satisfy constraints while not sacrificing data quality.  The case study investigates the respective capabilities retailers and transport providers have in predicting each other responses to a stated ranking exercise aimed at measuring agents’ preferences for alternative urban freight policies for the limited traffic zone. 


Smart inland shipping

The trend in inland vessel transportation is the focus on a more efficient (faster) transport through the rivers and other waterways by reducing waiting times and predicting Estimated Time of Arrival (ETA). The more efficient guidance of inland vessels in inland waterways often results in a problem for the ports and terminals at the end of the corridors. Vessels ‘pop out’ in an undesired order and at undesired moments which result in congestion at ‘holding berths/waiting berths’ and even prohibitions to enter ports. This causes congestion and even dangerous situations in urban areas by vessels no longer allowed to move towards a port or terminal. By analysing the available data, it should be possible to prove that just focusing on transition in waterways, does not necessarily result in a more efficient handling of cargo. Instead, tuning of the efficiency at locks and bridges, and a planning along the chain, should provide a controlled progress of the inland vessels, thus providing a ‘just in time’ and ‘orderly’ approach of the vessels.

Optimized transport and improved customer service

Several transport and logistics companies want to optimize its transportation network to reduce customer dissatisfaction and improve customer experience. Mostly service failures are causing customer dissatisfaction. Efficient use of data and information for optimizing the capacity of the transport network is vital issue. The case study consolidates distribution and logistics data, and utilized network analytics for determining the best node and hub model and transportation planning. The study will map customer complaints across various routes to identify the service delay as the major reason, and will consider channel optimization analytics and customer analytics for efficient service delivery. 


Big data and intelligent transport systems

Intelligent transport systems (ITS) apply information, data processing, communication, and sensor technologies to vehicles (including cars, trucks, trains, aircraft and ships), transport infrastructure and transport users to increase the effectiveness, environmental performance, safety, resilience and efficiency of the transport system.  Europe already has many examples of ITS in operation. For instance, real-time systems to tell public transport users when their bus or train can be expected to arrive; variable message signs and ramp signalling on motorways; parking and blind spot warning systems in cars; and systems to help aircraft follow safe routes to and from airports. As computer technology becomes both cheaper and more powerful, more ITS technologies will be deployed in Europe over time. Especially with the development of innovative big data processing technolgies, capable of handling real-time streaming data such as sensor data from vehicles or infrastructure, new digital services and systems are expected to create additional value for the end users.  In this case study, LeMO consortium will take a multimodal, multiagency approach to provide useful suggestions on the prerequisites of successful big data implementation in ITS.