Evaluation of Machine Learning Methods for the Prediction of Key Properties for Novel Transparent Semiconductors
ORAL
Abstract
Transparent conductors are crucial for the operation of a variety of technological devices such as photovoltaic cells and light-emitting diodes; however, only a small number of compounds are currently known to display both transparency and conductivity suitable enough to be used as transparent conducting materials. To address the need for finding new materials with an ideal functionality, an open big-data competition was organized by Novel Materials Discovery Repository (NOMAD) and hosted by Kaggle for the prediction both the formation enthalpy (an indication of stability) and the bandgap energy (an indication of optical transparency) for a dataset of ca. 3000 group-III oxide binary, ternary and quaternary alloys.
The performance of several machine-learning models (such as the sure independence screening and sparsifying operator [SISSO], the many-body tensor representation, subgroup discovery, random forests, support vector machines, etc) wil be summerized. A key realization from this examination is the importance of including local atomic information as input features or descriptors for the prediction of materials properties that can vary substantially with lattice site decorations.
The performance of several machine-learning models (such as the sure independence screening and sparsifying operator [SISSO], the many-body tensor representation, subgroup discovery, random forests, support vector machines, etc) wil be summerized. A key realization from this examination is the importance of including local atomic information as input features or descriptors for the prediction of materials properties that can vary substantially with lattice site decorations.
–
Presenters
-
Christopher Sutton
- Fritz Haber Institute of the Max Planck Society
- Theory , Fritz-Haber Institute
- Chemistry, Duke University
- Theory Department, Fritz Haber Institute