An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties

Ren, Zekun; Tian, Siyu; Noh, Juhwan; Oviedo, Felipe; Xing, Guangzong; Li, Jiali; Liang, Qiaohao; Zhu, Ruiming; Aberle, Armin G.; Sun, Shijing; Wang, Xiaonan; Liu, Yi; Li, Qianxiao; Senthilnath, J.; Hippalgaonkar, Kedar; Jung, Yousung; Buonassisi, Tonio

doi:10.1016/j.matt.2021.11.032

Cited by 102 publications

(141 citation statements)

References 36 publications

Supporting

Mentioning

140

Contrasting

Order By: Relevance

“…[329,330] Although most of the current application of generative models at the atomistic scale focused on small molecules, few practical cases of solid state materials have been demonstrated. [331][332][333] At the microstructure scale, generative models for solid materials have been very successful even for complex heterogeneous systems and limited datasets. [325,[328][329][330][334][335][336][337] Generative models can be used for inverting the design process of better battery interphases by going from properties to structure-and composition-conditional generative models that learn correlations in structural space conditioned to the properties.…”

Section: Inverse Generative Designmentioning

confidence: 99%

Modeling the Solid Electrolyte Interphase: Machine Learning as a Game Changer?

Diddens

Appiah

Mabrouk

et al. 2022

Adv Materials Inter

View full text Add to dashboard Cite

The solid electrolyte interphase (SEI) is a complex passivation layer that forms in situ on many battery electrodes such as lithium‐intercalated graphite or lithium metal anodes. Its essential function is to prevent the electrolyte from continuous electrochemical degradation, while simultaneously allowing ions to pass through, thus constituting an electronically insulating, but ionically conducting material. Its properties crucially affect the overall performance and aging of a battery cell. Despite decades of intense research, understanding the SEI's precise formation mechanism, structure, composition, and evolution remains a conundrum. State‐of‐the‐art computational modeling techniques are powerful tools to gain additional insights, although confronted with a trade‐off between accuracy and accessible time‐ and length scales. In this review, it is discussed how recent advances in data‐driven models, especially the development of fast and accurate surrogate simulators and deep generative models, can work with physics‐based and physics‐informed approaches to enable the next generation of breakthroughs in this field. Machine learning‐enhanced multiscale models can provide new pathways to inverse the design of interphases with desired properties.

show abstract

Section: Inverse Generative Designmentioning

confidence: 99%

Modeling the Solid Electrolyte Interphase: Machine Learning as a Game Changer?

Diddens

Appiah

Mabrouk

et al. 2022

Adv Materials Inter

View full text Add to dashboard Cite

show abstract

“…Solid state crystals structures owing to periodic boundary condition and inherent symmetries, are more challenging and thus only few practical cases have been demonstrated. [108,121,122] On the other hand, at the microstructural scale, generative models of solid materials have been very successful even for complex heterogeneous systems and limited datasets. [109,110,[115][116][117][123][124][125] Outstanding developments in convolutional networks in image processing and generation have been key to that success.…”

Section: Deep-learned Models and Explainable Aimentioning

confidence: 99%

Rechargeable Batteries of the Future—The State of the Art from a BATTERY 2030+ Perspective

Fichtner

Edström

Ayerbe

et al. 2021

Advanced Energy Materials

216

110

View full text Add to dashboard Cite

The development of new batteries has historically been achieved through discovery and development cycles based on the intuition of the researcher, followed by experimental trial and error—often helped along by serendipitous breakthroughs. Meanwhile, it is evident that new strategies are needed to master the ever‐growing complexity in the development of battery systems, and to fast‐track the transfer of findings from the laboratory into commercially viable products. This review gives an overview over the future needs and the current state‐of‐the art of five research pillars of the European Large‐Scale Research Initiative BATTERY 2030+, namely 1) Battery Interface Genome in combination with a Materials Acceleration Platform (BIG‐MAP), progress toward the development of 2) self‐healing battery materials, and methods for operando, 3) sensing to monitor battery health. These subjects are complemented by an overview over current and up‐coming strategies to optimize 4) manufacturability of batteries and efforts toward development of a circular battery economy through implementation of 5) recyclability aspects in the design of the battery.

show abstract

“…Several working directions are investigated for the generation of new materials. [ 8–16 ] There are mainly three different ways to generate or discover new crystal structures including doping/element substitution, [ 5,17–19 ] composition generation plus crystal structure prediction, [ 9 ] and generative machine learning models. [ 12,14–16,20,21 ] The element substitution approach is the most widely used strategy.…”

Section: Introductionmentioning

confidence: 99%

“…[ 8–16 ] There are mainly three different ways to generate or discover new crystal structures including doping/element substitution, [ 5,17–19 ] composition generation plus crystal structure prediction, [ 9 ] and generative machine learning models. [ 12,14–16,20,21 ] The element substitution approach is the most widely used strategy. But it is subject to the extremely limited known prototype structures in the database compared to the vast chemical design space.…”

Section: Introductionmentioning

confidence: 99%

“…One of the most promising approaches for new materials structure creation is deep generative machine learning models. [ 12–16,25–27 ] Both variational autoencoder (VAE) [ 14,15,26,27 ] and generative adversarial networks (GAN) [ 12,13,16,25 ] have been adapted for inverse design of inorganic materials with different crystal structure representations. A VAE model contains two parts: an encoder and a decoder.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High‐Throughput Discovery of Novel Cubic Crystal Materials Using Deep Generative Neural Networks

Zhao

Al-Fahdi

et al. 2021

Advanced Science

View full text Add to dashboard Cite

High-throughput screening has become one of the major strategies for the discovery of novel functional materials. However, its effectiveness is severely limited by the lack of sufficient and diverse materials in current materials repositories such as the open quantum materials database (OQMD). Recent progress in deep learning have enabled generative strategies that learn implicit chemical rules for creating hypothetical materials with new compositions and structures. However, current materials generative models have difficulty in generating structurally diverse, chemically valid, and stable materials. Here we propose CubicGAN, a generative adversarial network (GAN) based deep neural network model for large scale generative design of novel cubic materials. When trained on 375 749 ternary materials from the OQMD database, the authors show that the model is able to not only rediscover most of the currently known cubic materials but also generate hypothetical materials of new structure prototypes. A total of 506 such materials have been verified by phonon dispersion calculation. Considering the importance of cubic materials in wide applications such as solar panels, the GAN model provides a promising approach to significantly expand existing materials repositories, enabling the discovery of new functional materials via screening. The new crystal structures discovered are freely accessible at www.carolinamatdb.org.

show abstract

An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties

Cited by 102 publications

References 36 publications

Modeling the Solid Electrolyte Interphase: Machine Learning as a Game Changer?

Modeling the Solid Electrolyte Interphase: Machine Learning as a Game Changer?

Rechargeable Batteries of the Future—The State of the Art from a BATTERY 2030+ Perspective

High‐Throughput Discovery of Novel Cubic Crystal Materials Using Deep Generative Neural Networks

Contact Info

Product

Resources

About