Click For Photo: https://scx2.b-cdn.net/gfx/news/2020/inversedesig.jpg
The ability to generate optimized nanomaterials with artificial neural networks can significantly revolutionize the future of materials design in materials science. While scientists had progressively created small and simple molecules, complex crystalline porous materials remain to be generated using neural networks. In a recent report on Science Advances, Baekjun Kim and a team of researchers in the Department of Chemical and Biomolecular Engineering at the Korea Advanced Institute of Science and Technology, Republic of Korea, implemented a generative adversarial network.
They produced 121 crystalline porous materials using a training set of 31,713 known zeolites. The new neural network took input in the form of energy and materials dimensions to reliably produce zeolites with a user-desired range of 4 kJ/mol methane heat of adsorption. They designated the energy dimension in the work to be the methane potential energy. The fine-tuning of user-desired capability can potentially accelerate materials development, while demonstrating a successful case of inverse design of porous materials.
Materials - Scientists - Research - Materials - Intelligence
Materials scientists have conducted significant research to discover new materials using artificial intelligence in the past few years. They made considerable progress using a variety of artificial neural networks (ANNs) to generate undiscovered molecules and materials. However, ANNs remain to be successfully used to create new crystalline materials, since machine learning had thus far only predicted materials properties, compositions, bandgap energy, formation energy and gas adsorption uptakes. Crystalline porous materials contain dense arrangements of microscopic pores for higher surface area and pore volume. They are an important class of materials for a variety of diverse energy- and environment- related applications. Compared to other crystalline materials, porous materials such as zeolites, metal organic frameworks (MOFs) and covalent organic frameworks (COFs) are comparatively more challenging to generate using ANNs due to greater complexity.
In this study, Kim et al. devised an ANN to generate crystalline porous materials...
Wake Up To Breaking News!