- What can Data Analytics provide to research projects in mobility and transport?
The past two decades have seen an increase in the trend of commuting from rural to urban areas. As cities become more complex and dynamic, they struggle with new mobility challenges such as air pollution, traffic congestion and resource allocation. Additionally, new transport models are emerging over time, such as ridesharing, micro scooters, etc.
On the other hand, the availability of geo-spatial data generated by users (through the combination of social media systems and the wide use of smart devices) and connected transport modes (such as connected cars) creates new opportunities for city and transport planners, administrators and policymakers in general to acquire all the knowledge needed to plan for the future of urban mobility.
The available data are useless if not processed and transformed into something that can be easily understood by a transport domain expert. Indeed, the available data often come in raw format and are not immediately interpretable. In this case, data analytics play a fundamental role in undertaking a preliminary processing of raw data. Large amounts of data are interpreted to discover patterns, correlations, and other insights that help decision makers to make informed choices and researchers to proceed with mobility studies.
A few examples of tasks that could be performed through data analytics in the mobility and transport domain are:
- Identification of user mobility patterns;
- Identification of factors that impact the quality of user trips;
- Air pollution analysis;
- Congestion prediction;
- Synchronization of door-to-door multimodal trips;
Of course, the type of analysis performed is always related to the type of available data.
- In your opinion, what are the trends in using data analytics for unveiling mobility and transport patterns?
Data analytics plays an important role for the study of transport and mobility patterns. Indeed, on the one hand, it would not be possible to analyse such a huge amount of available data without specific tools such as those provided by the field of data analytics. On the other hand, the same type of study could not be performed using “classical approaches” like surveys and interviews, which are often characterized by high costs, small data samples and limited effectiveness in space and time.
That being said, the current trends consist of collecting or accessing multiple sources of data that come from sensors, user devices such as mobile phones, smart transportation systems, etc., to feed data analytics algorithms and models and to perform different types of analyses. For example, such data collection processes uncover mobility patterns, spatial analysis, prediction of traffic congestion, air pollution studies, resources optimization, etc. that can help mobility planners and decision maker in making informed choices.
- Which techniques / technologies will be used in the MoTiV project to analyse the data collected and to identify mobility patterns?
“Big Data” analytics include a wide range of specific tools and techniques for extracting, cleaning, transforming, modelling and visualizing data, with the objective of uncovering meaningful and useful information that can lead to significant conclusions and that in turn affect decision making processes. In the context of the MoTiV project, an exploratory data analysis approach will perform a preliminary investigation on the available data. As a first instance, the exploratory analysis has the purpose of spotting anomalies and testing preliminary hypotheses and assumptions. In a second phase, computational methods and data mining algorithms are exploited to uncover different segments of users and to analyse the mobility patterns that characterize and distinguish each segment.
- What is Eurecat’s role in MoTiV project?
In the context of the MoTiV project, Eurecat will lead the study of possible socio-economic and environmental factors that may affect the mobility of the users and will contribute to the MoTiV data collection campaign in Spain.
Using the data collected from users through the Woorti mobile app, Eurecat will detect behavioural patterns in the mobility of users and match them with some qualitative variables to assess how user behaviour matches with their propositions. Further activities include the cost-benefit analysis on the role of socio-economic and environmental factors in the mobility choices of users and the assessment of the most relevant factors that impact user travel experience.
In addition, Eurecat will also be responsible for the publication of an open version of the dataset used in the MoTiV project.