Search

The process of design and discovery of new materials can be significantly expedited and simplified if we can learn effectively from available data. Deep learning (DL) approaches have recently received a lot of interest for their ability to speed up the design of novel materials by predicting material properties with precision close to experiments and ab-initio calculations. The application of deep learning to predict materials properties measured by experiments are valuable yet challenging due to the limited amount of experimental data. Most of the existing approaches to predict properties from computational data have also been directed towards specific material properties. In this work, we extend this approach, by proposing Landscape Crystal Graph Convolution Network(LCGCN), an accurate and transferable deep learning framework based on graph convolutional networks. LCGCN directly learns the potential energy surface (PES) from atomic configurations. This approach can enable transferable models that can predict different material properties. We apply this framework to bulk crystals (i.e. Al2O3), and test it by calculating potential energy surfaces at different temperatures and across different phases of crystal.

Developing accurate, transferable and computationally inexpensive machine learning models can rapidly accelerate the discovery and development of new materials. Some of the major challenges involved in developing such models are, (i) limited availability of materials data as compared to other fields, (ii) lack of universal descriptor of materials to predict its various properties. The limited availability of materials data can be addressed through transfer learning, while the generic representation was recently addressed by Xie and Grossman [1], where they developed a crystal graph convolutional neural network (CGCNN) that provides a unified representation of crystals. In this work, we develop a new model (MT-CGCNN) by integrating CGCNN with transfer learning based on multi-task (MT) learning. We demonstrate the effectiveness of MT-CGCNN by simultaneous prediction of various material properties such as Formation Energy, Band Gap and Fermi Energy for a wide range of inorganic crystals (46774 materials). MT-CGCNN is able to reduce the test error when employed on correlated properties by upto 8%. The model prediction has lower test error compared to CGCNN, even when the training data is reduced by 10%. We also demonstrate our model's better performance through prediction of end user scenario related to metal/non-metal classification. These results encourage further development of machine learning approaches which leverage multi-task learning to address the aforementioned challenges in the discovery of new materials. We make MT-CGCNN's source code available to encourage reproducible research., Comment: NIPS Workshop on Machine Learning for Molecules and Materials

The pursuit of more advanced electronics, finding solutions to energy needs, and tackling a wealth of social issues often hinges upon the discovery and optimization of new functional materials that enable disruptive technologies or applications. However, the discovery rate of these materials is alarmingly low. Much of the information that could drive this rate higher is scattered across tens of thousands of papers in the extant literature published over several decades, and almost all of it is not collated and thus cannot be used in its entirety. Many of these limitations can be circumvented if the experimentalist has access to systematized collections of prior experimental procedures and results that can be analyzed and built upon. Here, we investigate the property-processing relationship during growth of oxide films by pulsed laser deposition. To do so, we develop an enabling software tool to (1) mine the literature of relevant papers for synthesis parameters and functional properties of previously studied materials, (2) enhance the accuracy of this mining through crowd sourcing approaches, (3) create a searchable repository that will be a community-wide resource enabling material scientists to leverage this information, and (4) provide through the Jupyter notebook platform, simple machine-learning-based analysis to learn the complex interactions between growth parameters and functional properties (all data and codes available on https://github.com/ORNL-DataMatls). The results allow visualization of growth windows, trends and outliers, and which can serve as a template for analyzing the distribution of growth conditions, provide starting points for related compounds and act as feedback for first-principles calculations. Such tools will comprise an integral part of the materials design schema in the coming decade., Comment: 30 pages; 8 figures