Learning formation energy of inorganic compounds using matrix variate deep Gaussian process
This work addresses the bottleneck of high computational costs in material design for engineering applications, though it is incremental in improving machine learning emulators for quantum calculations.
The paper tackled the problem of predicting formation energy for inorganic compounds by proposing a deep Gaussian process approach with a novel molecular descriptor, enabling implementation with small datasets.
Future advancement of engineering applications is dependent on design of novel materials with desired properties. Enormous size of known chemical space necessitates use of automated high throughput screening to search the desired material. The high throughput screening uses quantum chemistry calculations to predict material properties, however, computational complexity of these calculations often imposes prohibitively high cost on the search for desired material. This critical bottleneck is resolved by using deep machine learning to emulate the quantum computations. However, the deep learning algorithms require a large training dataset to ensure an acceptable generalization, which is often unavailable a-priory. In this paper, we propose a deep Gaussian process based approach to develop an emulator for quantum calculations. We further propose a novel molecular descriptor that enables implementation of the proposed approach. As demonstrated in this paper, the proposed approach can be implemented using a small dataset. We demonstrate efficacy of our approach for prediction of formation energy of inorganic molecules.