Data-driven site characterization using geotechnical and geophysical data (RDF23/MCE/Qi)

   Faculty of Engineering and Environment

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Xiaohui Qi, Prof Michael Lim  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Digital technologies and big data are transforming all aspects of industry including designs, builds, operations, and maintenance of infrastructures. Geotechnical engineering is lagging far behind other disciplines, partly because of its reliance on empiricism and the lack of access to large datasets. With the fast development in both the modelling methodologies and measurement technologies such as new field test equipment, geophysics and numerical software, there is a pressing need for geotechnical engineering to keep pace to enjoy the full benefits of digital revolution such as increased productivity and sustainability. Given that the knowledge of a site is central and indispensable to any civil engineering project, data-driven site investigation must be one of the key applications in data transformation in geotechnical engineering.

The key purpose of site investigation is to explore the underground conditions of a site, such as identifying the geotechnical properties of soil and the geological profile. Data-driven site investigation is a challenging task as the real-world data in geotechnical engineering are usually “ugly”, which typically have the attributes of MUSIC-3X, i.e., Multivariate, Uncertain and Unique, Sparse, Incomplete, three-dimensional and potentially Corrupted with ‘‘X” denoting the spatial/temporal variability. Multivariate means normally different tests are performed, leading to correlated test data while uncertain and unique suggest every site is unique and unrepeatable. Sparse and incomplete indicate that the tests are usually carried out at selected limited depths and few locations. In a deterministic paradigm, the measured ugly data are usually used to derive a single characteristic value or geological profile used as input of physical modelling, during which most data are discarded. It is rarely realized that ugly data can be used indirectly to support decision-making in a probabilistic paradigm. It is neither economic nor wise to discard the data. Furthermore, there are no satisfactory machine learning methods that can deal with the big indirect data explicitly and well incorporate the human experience.

This research project will develop a three-dimensional spatially variable geological profile using different sources of data such as cone penetration tests and geophysical data. The unique features of the geological models are as follows. (i) The uncertainty in the geological profile (e.g., location, extension, thickness of geological layers) will be quantified to reflect the complexity of the underground condition, quantity and quality of the data. (2) The used data-driven method has good explainability in the sense that the machine learning method is not a black box, and the output can be explained from a physical basis. (3) Human knowledge and judgement will be incorporated into the model to enable continuous refinement of the model. The research outcomes will provide a new way of decision-making for future site investigation and underground construction activities.

The successful Ph.D. student will be supported by leading experts in the field of data analysis, engineering geology as well as laboratory testing. The prospective student also has the opportunity to work in our new geotechnical laboratory facilities and have access to our advanced programming software and site investigation data from industrial collaborators.

Academic Enquiries

This project is supervised by Dr. Xiaohui Qi. For informal queries, please contact [Email Address Removed]. For all other enquiries relating to eligibility or application process please use the email form below to contact Admissions. 

Funding Information

Home and International students (inc. EU) are welcome to apply. The studentship is available to Home and International (including EU) students and includes a full stipend at UKRI rates (for 2022/23 full-time study this is £17,668 per year) and full tuition fees. Studentships are also available for applicants who wish to study on a part-time basis over 5 years (0.6 FTE, stipend £10,600 per year and full tuition fees) in combination with work or personal responsibilities).  

Please also see further advice below of additional costs that may apply to international applicants.

Eligibility Requirements:

  • Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
  • Appropriate IELTS score, if required.
  • Applicants cannot apply for this funding if they are already a PhD holder or if currently engaged in Doctoral study at Northumbria or elsewhere.

Please note: to be classed as a Home student, candidates must meet the following criteria:

  • Be a UK National (meeting residency requirements), or
  • have settled status, or
  • have pre-settled status (meeting residency requirements), or
  • have indefinite leave to remain or enter.

If a candidate does not meet the criteria above, they would be classed as an International student.  Applicants will need to be in the UK and fully enrolled before stipend payments can commence, and be aware of the following additional costs that may be incurred, as these are not covered by the studentship.

  • Immigration Health Surcharge
  • If you need to apply for a Student Visa to enter the UK, please refer to the information on It is important that you read this information very carefully as it is your responsibility to ensure that you hold the correct funds required for your visa application otherwise your visa may be refused.
  • Check what COVID-19 tests you need to take and the quarantine rules for travel to England
  • Costs associated with English Language requirements which may be required for students not having completed a first degree in English, will not be borne by the university. Please see individual adverts for further details of the English Language requirements for the university you are applying to.

How to Apply

For further details of how to apply, entry requirements and the application form, see   

For applications to be considered for interview, please include a research proposal of approximately 1,000 words and the advert reference (e.g. RDF23/…).

Deadline for applications: 27 January 2023

Start date of course: 1 October 2023 tbc

Engineering (12) Mathematics (25)


Yang, Z., Li, X., Qi, X., 2022. Efficient simulation of multivariate three-dimensional cross-correlated random fields conditioning on non-lattice measurement data. Computer Methods in Applied Mechanics and Engineering 388, 114208.
Qi, X., Wang, H., Pan, X., et al., 2021. Prediction of interfaces of geological formations using the multivariate adaptive regression spline method. Underground Space 6, 252-266.
Qi, X., Pan, X., Chiam, K., et al., 2020. Comparative spatial predictions of the locations of soil-rock interface. Engineering Geology 272, 105651.
Qi, X.-H., Li, D.-Q., Phoon, K.-K., et al., 2016. Simulation of geologic uncertainty using coupled Markov chain. Engineering Geology 207, 129-140.

How good is research at Northumbria University in Engineering?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Where will I study?

 About the Project