PhD Student (f/m/d) - Machine-learning Mesoscale Simulation Framework for HED Phenomena / very good university degree (Master/Diploma) in physics or in a related subject / Generate high-fidelity training data for materials under HED …

Helmholtz-Zentrum Dresden-Rossendorf (HZDR)

Görlitz, Germany

Area of research:

PHD Thesis



Part-Time Suitability:

The position is suitable for part-time employment.



Starting date:

1596232800



Job description:


PhD Student (f/m/d) – Machine-learning Mesoscale Simulation Framework for HED Phenomena


A member of the Helmholtz Association of German Research Centers, the HZDR employs about 1,200 people. The Center’s focus is on interdisciplinary research in the areas energy, health and matter.


The Center for Advanced Systems Understanding (CASUS) is a German-Polish research center for dataintensive digital systems research. We combine innovative methods from mathematics, theoretical systems research, simulations, data science, and computer science to provide solutions for a range of disciplines – materials science under ambient and extreme conditions, earth system research, systems biology, and autonomous vehicles.


CASUS was jointly founded in August 2019 by the Helmholtz-Zentrum Dresden-Rossendorf, the Helmholtz Centre for Environmental Research. the Max Planck Institute of Molecular Cell Biology and Genetics. the Technical University of Dresden and the University of Wroclaw.


The Department on Matter under Extreme Conditions is looking for a PhD student (f/m/d) Machine-learning Mesoscale Simulation Framework for HED Phenomena.


The position will be available from now. The employment contract is limited to three years.


The Scope of Your Job


Your project will contribute to the ambitious long-term goal of achieving a more accurate and consistent understanding of high energy density (HED) phenomena in the warm dense regime across multiple length and time scales.
You are expected to develop a molecular dynamics (MD) simulation framework for predicting magnetic, electronic, and phononic degrees of freedom in HED matter at the mesoscale. The core of the simulation framework is the LAMMPS code which relies on interatomic potentials (IAPs). Based on high-fidelity training data generated using DFT-MD you will generate quantum-accurate IAPs by employing the Spectral Neighbor Analysis Potential (SNAP) methodology. You will explore various state-of-the-art machine learning models to capture the complexities of the electronic structure under HED conditions. Furthermore, you will verify the effectiveness of the simulation framework by calculating the kinetics of magneto-structural phase transitions in iron as a surrogate for many complex HED processes and phenomena. You will carry out your research in collaboration with our partners at international research institutions.


Tasks:


#

generate high-fidelity training data for materials under HED conditions (aluminum and silica) with DFT-MD



#

design and implement a computational machine-learning workflow to predict the LDOS, energies, and forces



#

implement and analyze several ML techniques and physics constraints in the ML-DFT workflow



#

compute the equations of state of aluminum and silica under ambient and HED conditions



#

publish your results in academic, peer-reviewed journals



#

present your results at scientific meetings




Requirements:


#

very good Diploma or Master’s degree in physics or in a related subject



#

a solid background in mathematics, physics, materials science, or in a related subject



#

excellent programming skills in languages such as Fortran, Python, or C/C++



#

experience in data generation with electronic structure (such as VASP, Quantum Espresso, Elk) and molecular dynamics (such as LAMMPS) codes



#

experience in data modeling with machine learning (such as Tensorflow, Pytorch)



#

strong motivation to work in a collaborative environment



#

excellent communication skills in English and in a professional context (presentation of research results at scientific meetings, colloquial discussions, writing of manuscripts)




We offer:


#

a vibrant research community in an open, diverse, and international work environment



#

scientific excellence and high quality



#

high scientific professional networking as well as scientific excellence



#

salary and social benefits in conformity with the provisions of the Collective Agreement TVöD-Bund (30 vacation days per year, company pension plan)



#

a good work/life balance for which we offer assistance in the shape of:


#

in-house health management



#

flexible working hours






Kindly submit your completed application (including cover letter, CV, diplomas/transcripts, etc.) only via our Online-application-system.


Please apply via recruiter’s website.

Quote Reference: NATURE:61120