Generating optimal nanomaterials using artificial neural networks can potentially lead to a notable revolution in future materials design. Although progress has been made in creating small and simple molecules, complex materials such as crystalline porous materials have yet to be generated using any of the neural networks. Here, we have implemented a generative adversarial network that uses a training set of 31,713 known zeolites to produce 121 crystalline porous materials. Our neural network takes in inputs in the form of energy and material dimensions, and we show that zeolites with a user-desired range of 4 kJ/mol methane heat of adsorption can be reliably produced using our neural network. The fine-tuning of user-desired capability can potentially accelerate materials development as it demonstrates a successful case of inverse design of porous materials.

In the past decade, there has been an increasing number of computational screening works to facilitate finding optimal materials for a variety of different applications. Unfortunately, most of these screening studies are limited to their initial set of materials and result in a brute-force type of screening approach. In this work, we present a systematic strategy that can find metal−organic frameworks (MOFs) with the desired properties from an extremely diverse and large set of over 100 trillion possible MOFs using machine learning and evolutionary algorithm. It is demonstrated that our algorithm can discover 964 MOFs with methane working capacity over 200 cm 3 cm −3 and 96 MOFs with methane working capacity over the current world record of 208 cm 3 cm −3 . We believe that this methodology can take advantage of the modular nature of MOFs and can readily be extended to other important applications as well.

No abstract

We have developed a simple text mining algorithm that allows us to identify surface area and pore volumes of metal-organic frameworks (MOFs) using manuscript html files as inputs. The algorithm searches for common units (e.g., m/g, cm/g) associated with these two quantities to facilitate the search. From the sample set data of over 200 MOFs, the algorithm managed to identify 90% and 88.8% of the correct surface area and pore volume values. Further application to a test set of randomly chosen MOF html files yielded 73.2% and 85.1% accuracies for the two respective quantities. Most of the errors stem from unorthodox sentence structures that made it difficult to identify the correct data as well as bolded notations of MOFs (e.g., 1a) that made it difficult identify its real name. These types of tools will become useful when it comes to discovering structure-property relationships among MOFs as well as collecting a large set of data for references.

Crystalline nanoporous materials (i.e. shapes) were generated in the energy space using an artificial neural network.