PhD: Advancing methods of rapid flood risk scenario assessment using hybrid approaches of hydraulic modelling and machine learning

 (via FindAPhD)
University of Canterbury
Christchurch, New Zealand
Position Type: 
Organization Type: 
University/Academia/Research/Think tank
Experience Level: 
Not Specified
Degree Required: 
Bachelor's (Or Equivalent)


Please note: this job post has expired! To the best of our knowledge, this job is no longer available and this page remains here for archival purposes only.

About the Project

We have an opening for motivated students to undertake PhD research that will improve the flood resilience of New Zealand communities through developing innovative flood modelling techniques. Two 3-year positions are available and will be supported by the New Zealand Government via the Ministry for Business, Innovation and Employment (MBIE) through a NIWA-led five-year Endeavour Programme on reducing flood risk in Aotearoa/New Zealand. The PhDs will be co-hosted by the School of Earth and Environment and the Geospatial Research Institute at the University of Canterbury in Christchurch, New Zealand, in conjunction with NIWA. An annual scholarship of NZ$30,000 plus fees is available to successful applicants. Both PhD projects will address aspects of flood modelling including issues surrounding climate change and will feed into and work with the wider group of Endeavour Programme researchers.

PhD project 2: Advancing methods of rapid flood risk scenario assessment using hybrid approaches of hydraulic modelling and machine learning.

The PhD project will be specifically focussing on a case study working with the Wairewa Runanga based near Little River, Canterbury, New Zealand. Current computing power means flood risk assessments are usually limited to a handful of scenarios for each catchment of interest. This PhD project will investigate the feasibility of using a hybrid hydrodynamic/ machine learning model to reduce the numerical modelling load and enable probabilistic modelling. The project will construct a population of large and extreme events based on multiple variables (rainfall duration and intensity, river flow, lake water level, etc) to understand what can lead to inundation and the relationship between drivers of inundation and events in Wairewa’s written and oral history. Selected scenarios will be modelled and the results of these will be used to train a machine learning algorithm to produce inundation maps for the remaining events. Results from this research will provide the tools to aid discussions with Wairewa Runanga and be used by the Endeavour Programme to develop a Matauranga Maori approach to flood resilience. This PhD will also be done in conjunction with Assoc. Prof Fernando Mendez and Dr Ana Rueda Zamora at Universidad de Cantabria, Santander, Spain.

Further information and applications

Computer literacy (e.g. Python, Matlab or similar), knowledge of hydraulic modelling and machine learning techniques are highly desirable. Numeracy and excellent written and oral communication skills are essential. The candidates should expect to interact with a multidisciplinary team of researchers throughout Aotearoa/New Zealand and internationally. The research results will have global applications to flood prone regions and will be published in national and international peer-reviewed journals.

Please direct all enquiries to the project co-supervisors Dr. Emily Lane (NIWA Taihoro Nukurangi, ) and Prof. Matt Wilson (University of Canterbury, ). Applications should be sent by email care of the GRI Manager, Dr. Melanie Tomintz () no later than 31 January 2021. Please submit the following documents as part of your application:

  1.  A full curriculum vitae, including details of any prior publications;
  2. A cover letter outlining your motivation and suitability for the research project;
  3. Contact details of at least two referees; and
  4. A GPA report obtained from (those with New Zealand or United States qualifications are not required to use Scholaro).

In your correspondence and cover letter please indicate if you have a preferred PhD project.