KDnuggets Home » Academic » Heriot-Watt University: PhD studentships in Data Science Approaches to Subsurface Reservoirs Management ( 14:n30 )

Heriot-Watt University: PhD studentships in Data Science Approaches to Subsurface Reservoirs Management


PhD studentships in Data Science Approaches to Subsurface Reservoirs Management are available to candidates with strong computational skills and experience in applying machine learning. Applications due December 1st.



Heriot-Watt University At: Heriot-Watt University
Location: Scotland, UK
Web: www.pet.hw.ac.uk/
Position: PhD studentships in Data Science Approaches to Subsurface Reservoirs Management

PhD studentships in Data Science Approaches to Subsurface Reservoirs Management

The Institute of Petroleum Engineering (IPE) at Heriot-Watt University (Scotland, UK) is looking for several PhD candidates to work on a project titled "Data Science Approaches to Subsurface Reservoirs Management" under the supervision of Dr Ahmed H. Elsheikh (http://www.pet.hw.ac.uk/staff-directory/ahmed-elsheikh.htm).

Project outline:

Observations and numerical simulations of subsurface flow systems are currently generating massive amounts of data. The challenges of handling these massive datasets go beyond the standard big-data issues (distributed storage, spatial and time indexing, and subsequent querying operation). The focus of the current project is to build data analysis pipelines that can turn these data-sets into predictive models to support decision making and risk assessment. Sample work packages include the following PhD projects:

  1. Observational data is collected in real time, producing data streams that can overwhelm standard data analysis pipelines. This PhD project will address the desire to make rapid decisions in near real time via a hybrid data-driven, physics-based approach. This could build on reinforcement learning techniques combined with reduced order physical models.
  2. Analysis of spatial and temporal data sets from different sources is a challenging problem. This PhD project will focus on representation learning while maintaining coherence across spatial and temporal scales as well as physical validity. This can build on lessons learned from deep learning approaches combined with a hierarchy of physical models with different levels of details.
  3. Rare and extreme events are largely overlooked in the operational planning and management workflows of subsurface reservoirs. This is attributed to difficulties of the model calibration process in the presence of heavy tailed distributions. This project will focus on design of risk-aware pipelines for data analysis and model calibration of subsurface flow models.
Essential skills:

  • Masters degree in computational mathematics, physics or in a relevant engineering discipline with strong computational skills.
  • Programming skills preferably in Python and C++.
  • Ability to write reports, collate information and present it in a clear and engaging manner.
  • Excellent communication skills.

Desirable skills:

  • Machine learning techniques.
  • Bayesian statistics and probabilistic graphical models.
  • Numerical optimisation.
  • Computational methods for PDEs.

Fees and funding:

  • These PhD studentships are available to UK/EU/Overseas candidates. It includes tuition fees and an appropriate stipend for three years at the EPSRC recommended levels.

Application process:

Interested individuals are invited to email the documents and information listed below to the project leader (Dr. Ahmed H. Elsheikh; email: ahmed.elsheikh@pet.hw.ac.uk)

  • Cover letter including areas of expertise and research interests.
  • Current curriculum vitae.
  • Degree certificates and transcripts (undergraduate and graduate).
  • Evidence of excellence and verifiable list of programming skills.
  • Contact information of at least three (3) referees.

Closing date: 1st of December 2014

We invite research leaders and ambitious early career researchers to join us in leading and driving research in key inter-disciplinary themes. Please see www.hw.ac.uk/researchleaders for further information and how to apply.

Heriot-Watt University is a Scottish charity

registered under charity number SC000278.

Sign Up

By subscribing you accept KDnuggets Privacy Policy