Materials Informatics: An Algorithmic Design Rule Comparison

We have investigated the organic semiconductor's enigmas through the material informatics approach. We have used the Open Quantum Materials Database (OQMD), one of the largest open databases of calculated materials properties. We have developed data-driven methods for novel organic semiconductor discovery for electronic application and knowledge extraction. In the organic semiconductor molecular design through variational autoencoders (VAE) combining convolutional neural networks (CNN) as encoder and recurrent neural network (RNN) as decoder section. We have investigated a deep learning (DL) design to predict quantitatively accurate and desirable material properties by constructing a relationship between the molecular structure and its property through a material graph-based neural network. In the variational autoencoders (VAE) combining convolutional neural networks (CNN) as encoder and recurrent neural network (RNN) as decoder section