Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Geotechnical assessment of ground settlement and soil-structure interactions based on data analytics and machine learning techniques for sensor-driven smart highways


   School of Engineering and Built Environment

   Applications accepted all year round  Competition Funded PhD Project (Students Worldwide)

About the Project

The project aims to develop a geotechnical-based interactive analytical road health monitoring and predictive system for smart highways of the future, via machine learning techniques and data transmission protocols. This PhD project forms part of a successful Australian Research Council Linkage Program (ARC LP) grant.

The construction of highway embankments on problematic soils (i.e., highly compressible or soft clays, and peaty soils) can pose great construction challenges if their characteristics are not fully understood. It is proposed to initiate a structured and evidence-based solution to monitor the performance of roads to minimise risks associated to construction safety and to improve road network resilience.

In some field instrumentation studies, the long-term settlement of road embankments constructed on soft deposits in the South East Queensland was found to be underestimated up to 60%, leading to excessive post-construction settlements. This shows that a long-term geotechnical instrumentation program is essential to ensure project safety and to monitor the performance of road embankments due to significant time-dependent deformations under a constant-stress (post-construction) phenomenon.

The customised pro-active risk management system is expected to provide ample warning so that potential major disasters can be mitigated. Finite element analyses, field observational methods and machine learning techniques will be deployed to create a robust predictive framework to forward-predict the performance of roads as a result of soil-infrastructure interactions.

The PhD candidate, preferably with (i) degree(s) in BEng(Hons.) and/or Master in Civil/Geotechnical Engineering, (ii) an interest in Machine Learning and (iii) at least 2 first-author publications in international peer-reviewed journals, will have the opportunity to collaborate with design engineers, civil contractors and IT programmers to gain a comprehensive work experience and also an opportunity for future employment with the project’s industry partners.

The successful PhD candidate is expected to fulfil all of Griffith University’s PhD selection criteria. It is expected that the PhD candidate be based in-person on Griffith’s Nathan campus in Brisbane, Queensland, Australia, even though some travels to Griffith’s Gold Coast campus is also expected.

Funding Notes

  • Griffith University funds both domestic and international PhD candidates on a competitive basis and is one of few institutions to offer both a tuition fee waiver and a living stipend.
  • To be eligible and competitive for a Griffith University Postgraduate Research Scholarship (domesticView Website) or a Griffith University International Postgraduate Research Scholarship (international applicants; View Website) you need to have First Class Honours or equivalent research experience.
  • First-author peer-reviewed publications in international journals are advantageous.
  • Top-ranked candidates will be selected from among applicants to proceed to a formal PhD and scholarship application through Griffith University, with the support of the prospective supervisory team.
  • Applications can be received and processed year-round for our four intakes. Click here for key dates.
Architecture, Building & Planning (3) Computer Science (8) Engineering (12) Geology (18)

Register your interest for this project