Stefanos Papanikolaou

Department: 
NOMATEN
Group: 
Materials Structure, Informatics and Function
Personal webpage: 

http://nomaten.ncbj.gov.pl/

Research focus: 

Materials Informatics, Multiscale Materials Modeling, Statistical Mechanics, alloy composition search and machine learning, Machine learning of strain images, machine learning of interatomic potentials

ML expertise / Scientific Expertise: 

Unsupervised Machine Learning using Principal Component Analysis and complex clustering,
Supervised Machine Learning using deep convolutional neural networks (Tensorflow), Decision Trees, Support Vector Machines (sklearn)

Relevant publications: 
  1. Papanikolaou, S., 2020. Microstructural inelastic fingerprints and data-rich predictions of plasticity and damage in solids. Computational Mechanics, 66(1), pp.141-154. https://link.springer.com/article/10.1007/s00466-020-01845-x
  2. Yang, Z., Papanikolaou, S., Reid, A.C., Liao, W.K., Choudhary, A.N., Campbell, C. and Agrawal, A., 2020. Learning to predict crystal plasticity at the nanoscale: Deep residual networks and size effects in uniaxial compression discrete dislocation simulations. Scientific reports, 10(1), pp.1-14. https://www.nature.com/articles/s41598-020-65157-z
  3. Papanikolaou, S. and Tzimas, M., 2019. Effects of rate, size, and prior deformation in microcrystal plasticity. Mechanics and Physics of Solids at Micro‐and Nano‐Scales, pp.25-54.
  4. Papanikolaou, S., Tzimas, M., Reid, A.C. and Langer, S.A., 2019. Spatial strain correlations, machine learning, and deformation history in crystal plasticity. Physical Review E, 99(5), p.053003. https://journals.aps.org/pre/abstract/10.1103/PhysRevE.99.053003
Other: 

Enjoying drinking coffee during random hours