Tokamak reactors must fueled by cryogenic pellets. In addition, there is much evidence of pellet fueling playing a role in improved plasma confinement regimes. Fast and accurate modelling of pellet scenarios with integrated models would help understand and optimize these regimes. In addition, this modelling capability would benefit answering control-oriented questions such as fueling, burn, and exhaust control in pellet scenarios where incidents such as missing pellets can occur. This PhD position focuses on building up such capabilities for the JINTRAC multiphysics tokamak simulation suite1 , and then tackling the underlying research question of understanding and predicting pellet-enhanced confinement regimes. While JINTRAC, using first-principle-driven transport models, has been shown to accurately model pellet fueled scenarios2, the optimization and control-oriented nature of this project demands fast modelling and thus the extension of neural network surrogate models implemented within JINTRAC3. Experimental validation of the modelling pipelines will be carried out on existing data of a target tokamak to be determined (possibly ASDEX-Upgrade). To enable the research, the following tools must be developed.

• A fast surrogate pellet ablation and fueling model, using neural networks, of the HPI2 model
• Fast surrogate turbulence model valid for target tokamak regimes
  • Development of the QuaLiKiz neural network tailored to pellet scenarios on the target tokamak, using Active Learning techniques for data efficiency
  • Collecting a profile database of the target tokamak for sampling inputs for the NN training.
• Coupling the new surrogate models for JINTRAC "flight simulator" fast modelling
• Large-scale validation of JINTRAC + fast surrogate models in target tokamak pellet regimes
• Scenario optimization of pellet enhanced scenarios

The project combines tokamak physics research with elements from software engineering and machine learning. A solid background in both fields is beneficial, preferably MSc. in (fusion/plasma) physics with some experience in computational methods (knowledge in Python and Fortran an advantage), simulation, and/or machine learning.

1. Romanelli, M. et al. JINTRAC: A system of codes for integrated simulation of Tokamak scenarios. Plasma Fusion Res. 9, 1-4 (2014).
2. Marin, M., et al. "Multiple-isotope pellet cycles captured by turbulent transport modelling in the JET tokamak." Nuclear Fusion 61.3 (2021): 036042.
3. Ho, Aaron, et al. "Neural network surrogate of QuaLiKiz using JET experimental data to populate training space." Physics of Plasmas 28.3 (2021): 032305.

This position is for 1 FTE, will be for a period of 4 years and is graded in pay scale PhD. The position will be based at DIFFER (www.differ.nl) and the working location will be at TU Eindhoven. When fulfilling a position at DIFFER, you will have an employee status at NWO. You can participate in all the employee benefits NWO offers. We have a number of regulations that support employees in finding a good work-life balance. At DIFFER we believe that a workforce diverse in gender, age and cultural background is key to performing excellent research. We therefore strongly encourage everyone to apply. More information on working at NWO can be found at the NWO website (https://www.nwo-i.nl/en/working-at-nwo-i/jobsatnwoi/)

Dutch Institute for Fundamental Energy Research

The Dutch Institute for Fundamental Energy Research (DIFFER) performs leading fundamental research on materials, processes, and systems for a global sustainable energy infrastructure. We work in close partnership with (inter)national academia and industry. Our user facilities are open to industry and university researchers. As an institute of the Dutch Research Council (NWO) DIFFER plays a key role in fundamental research for the energy transition.

We use a multidisciplinary approach applicable on two key areas, solar fuels for the conversion and storage of renewable energy and nuclear fusion - as a clean source of energy.