Multi-Modal Data-Driven Solutions for Validating Policies in Transportation Systems
Lead Research Organisation:
Newcastle University
Department Name: Sch of Engineering
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
People |
ORCID iD |
| Roberto Palacin (Primary Supervisor) | |
| Farzaneh Farhadi (Student) |
Publications
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| EP/V519571/1 | 30/09/2020 | 29/09/2025 | |||
| 2518215 | Studentship | EP/V519571/1 | 11/01/2021 | 10/01/2025 | Farzaneh Farhadi |
| Description | Title: Data-Driven Solutions in Transport Systems Using Machine Learning and Optimisation Methods. Abstract: This research focuses on developing data-driven techniques that can integrate large diverse, and complex datasets in transportation for validating policies and implementing the policy commitments with case studies from clean air zone and electric vehicle charging infrastructure. To achieve this aim, we specifically address the following research questions: (a) Given the large volume of data gathered from the transportation network, what data types are relevant to a policy objective? (b) What are machine learning techniques suitable for combining large datasets, processing the data, and validating a policy objective? (c) Could these large dataset techniques be used for achieving a policy commitment? We have designed a framework to tackle the specific challenge of finding datasets that are related to the policy objective using machine learning techniques, and a framework for implementing policy commitments using multi-objective optimisations. Datasets from the Newcastle Urban Observatory and open-source datasets from the Department for Transport and National Statistics are used for this research with the policies of clean air zone and transition towards electric vehicles (EVs). The objectives of these policies are to reduce exposure to harmful levels of NO2 and CO2 and to expand the electric vehicle charging infrastructure to ensure that EV charging infrastructure meets the demand of the users. We use two data-driven approaches including machine learning models for the policy objectives and use simulation in combination with optimisation for implementing the policy commitment. |
| Exploitation Route | This research focuses on developing data-driven techniques that can integrate large diverse, and complex datasets in transportation for validating policies and implementing the policy commitments with case studies from clean air zone and electric vehicle charging infrastructure. |
| Sectors | Digital/Communication/Information Technologies (including Software) Environment Transport |
| URL | https://ieeexplore.ieee.org/document/9922587 |
| Description | Contributions with Case-funding partner, Arup, in constructing quantitative modelling for electric vehicle charging infrastructure. |
| Sector | Transport,Other |
| Impact Types | Policy & public services |