Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

Abstract

By combining metal nodes with organic linkers we can potentially synthesize millions of possible metal–organic frameworks (MOFs). The fact that we have so many materials opens many exciting avenues but also create new challenges. We simply have too many materials to be processed using conventional, brute force, methods. In this review, we show that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations. The first part of the review gives an introduction to the principles of big-data science. We show how to select appropriate training sets, survey approaches that are used to represent these materials in feature space, and review different learning architectures, as well as evaluation and interpretation strategies. In the second part, we review how the different approaches of machine learning have been applied to porous materials. In particular, we discuss applications in the field of gas storage and separation, the stability of these materials, their electronic properties, and their synthesis. Given the increasing interest of the scientific community in machine learning, we expect this list to rapidly expand in the coming years.

Understanding the diversity of the metal-organic framework ecosystem

“…The performance and accuracy of our models is comparable with the prior studies 14,[31][32][33][34][35] (see a comprehensive list in ref. 36 ). However, to be able to compare the accuracy and performance of different models and feature sets, one needs to perform a benchmark study using a fixed set of materials with high diversity and their corresponding properties as for example, we observe the performance of machine-learning models varies considerably from one database to another.…”

Large-Scale Free Energy Calculations on a Computational Metal–Organic Frameworks Database: Toward Synthetic Likelihood Predictions

“…Moreover, even when calculations on non-synthesizable MOFs are still valuable (e.g. for machine learning 63,85 ) a synthetic likelihood criterion could be used to downsize a database that is too large for simulations of a given computational cost.…”

Digital Transformation in Materials Science: A Paradigm Change in Material's Development

“…[38] The development of such software-based methods for material development of new materials is still in its infancy. However, there are first examples, such as the use of machinelearning for the predication of material properties, [59,68], for example, battery materials, [69,70] the use of machine learning and modeling for the targeted selection and subsequent synthesis of conductive MOFs, [71,72] the predication of metallic glasses [73] or the targeted development of catalysts. [57] The most significant challenge for machine-learning systems is the amount of data and the associated time (and resources) for the required experiments.…”