Inverse design of porous materials using artificial neural networks

Kim, Baekjun; Lee, Sang‐Won; Kim, Jihan

doi:10.1126/sciadv.aax9324

Cited by 245 publications

(167 citation statements)

References 34 publications

Supporting

Mentioning

166

Contrasting

Unclassified

Order By: Relevance

“…They can aid experiments in screening possible synthetic routes and suggesting the most affordable and efficient means. For example, inverse design, a technique predicting compositions and structures of starting materials based on end-of-use functions 15 , can accelerate the discovery of novel porous organic materials.…”

Section: Emerging Materials Development By Computation and Data Scienmentioning

confidence: 99%

Porous organic materials offer vast future opportunities

Liu

2020

Nat Commun

View full text Add to dashboard Cite

In light of the surging research on porous organic materials, we herein discuss the key issues of their porous structures, surface properties, and end functions. We also present an outlook on emerging opportunities, new applications, and data science-assisted materials discovery. Porous organic materials have diverse compositions and tunable pore sizes (Fig. 1), which have enabled a wide variety of applications including separation, filtration, storage, catalysis, and drug delivery. According to the International Union of Pure and Applied Chemistry definition, the pores in the porous organic materials are classified into micropores (<2 nm), mesopores (2-50 nm), and macropores (>50 nm). It is often beneficial for porous organic materials to possess hierarchical pores across multiple length scales. The size exclusion of these pores, as well as the physical and chemical interactions of molecules with pore surfaces, offer the porous organic materials tunable permeability and selectivity that are critical to their applications.

show abstract

Section: Emerging Materials Development By Computation and Data Scienmentioning

confidence: 99%

Porous organic materials offer vast future opportunities

Liu

2020

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Kim and co-workers started building GANs that can generate energy grids of zeolites 546 and recently extended their model to predict the structure of all-silica zeolites. 434 To do so, they used a separate channel (as is used for the RGB channels in color images) for oxygen and silicon atom positions which they encoded by placing Gaussian at the atom positions. By adjusting the loss function to target structures with a specific heat of adsorption, they could observe a drastic shift in the shape of the distribution of this property but not in the one for the void fraction or the Henry coefficient ( Figure 47 ).…”

Section: Applications Of Supervised Machine Learningmentioning

confidence: 99%

“… Distribution of Henry coefficient, void fraction and heat of adsorption for generated structures with a user-defined target range of 18–22 kJ mol –1 for the heat of adsorption. Reproduced from ref ( 434 ). …”

Section: Applications Of Supervised Machine Learningmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

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.

show abstract

“…There are so far no clear examples of the application of this approach to nanomaterials. In related fields, Kim et al recently reported the use of GANs in the inverse design of porous materials [68] and So and Rho used deep convolutional GANs to generate new nanophotonic structures by inverse design. [69] Gomez-Bombarelli et al showed how a DNN and a recurrent neural network (RNN) can be used as an encoder and the decoder, respectively, for inverse design.…”

Section: Inverse Designmentioning

confidence: 99%

Role of Artificial Intelligence and Machine Learning in Nanosafety

Winkler

2020

Small

108

View full text Add to dashboard Cite

Robotics and automation provide potentially paradigm shifting improvements in the way materials are synthesized and characterized, generating large, complex data sets that are ideal for modeling and analysis by modern machine learning (ML) methods. Nanomaterials have not yet fully captured the benefits of automation, so lag behind in the application of ML methods of data analysis. Here, some key developments in, and roadblocks to the application of ML methods are reviewed to model and predict potentially adverse biological and environmental effects of nanomaterials. This work focuses on the diverse ways a range of ML algorithms are applied to understand and predict nanomaterials properties, provides examples of the application of traditional ML and deep learning methods to nanosafety, and provides context and future perspectives on developments that are likely to occur, or need to occur in the near future that allow artificial intelligence to make a deeper contribution to nanosafety.

show abstract

Inverse design of porous materials using artificial neural networks

Cited by 245 publications

References 34 publications

Porous organic materials offer vast future opportunities

Porous organic materials offer vast future opportunities

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

Role of Artificial Intelligence and Machine Learning in Nanosafety

Contact Info

Product

Resources

About