Date: November 23, 2022Time: 11:45 am – 12:45 pm
Prof. Dr. Alessio Gagliardi
Technische Universität München, Electrical and Computer Engineering,
Munich Data Science Institute
Machine Learning to Investigate Material Properties
Machine learning (ML) is emerging as a new tool for many different fields which now span, among the others, chemistry, physics and material science [1,2]. The idea is to use ML algorithms as a powerful machinery to identify, starting from big data analysis, subtle correlations between simple elemental quantities and complex material properties and then use these to predict them. This approach can help to screen many material properties directly in-silico avoiding more computational expensive ab-initio calculations and experimental measurements.
However, adapting existing ML architectures to problems in chemistry, physics and material science is not straightforward. Several aspects need to be addressed to improve machine performance which can be summarized into prediction accuracy and generalization skills. Improving these aspects require to go into the details of the machine and analyze the way they learn from a training dataset. This allows to identify which architecture, training algorithm and dataset are relevant for the problem at hand.
In the present talk several methods will be presented to integrate with both theoretical and experimental data.
 Wei Li, Ryan Jacobs, Dane Morgan Computational Materials Science 150, 454-463 (2018)
 G. Pilania, A. Mannodi-Kanakkithodi, B. P. Uberuaga, R. Ramprasad, J. E. Gubernatis & T. Lookman, Scientific Reports volume 6, Article number: 19375 (2016).
Bio: Prof. Gagliardi research is on the development and application of numerical models for the simulation of nanostructured devices. His focus is on new solar cells (organic semiconductors based on perovskite), electrochemical systems (fuel cells, batteries) and organic semiconductor materials. The development of new models ranges from the nanoscale (Density Functional Theory, Quantum Green Functions) through the mesoscale (Kinetic Monte Carlo) to the macroscopic scale (drift diffusion, continuum models). He is also a developer of TiberCAD and the Green-DFTB software. His latest research is on multiscale modelling for organic semiconductors and the use of machine/deep learning approaches in material science.
After studying engineering at the University of Rome Tor Vergata (Italy), Professor Gagliardi received his doctorate in physics from the University of Paderborn in 2007. He later worked as a postdoc at the Bremen Center for Computing Materials and in Rome before being appointed Tenure Track Assistant Professor at TUM in 2014. Since 2020 he is Associate Professor at TUM.
For the password please contact Anastasia Barabash