Data-driven learning and prediction of inorganic crystal structures

Deringer, Volker L.; Proserpio, Davide M.; Csänyi, Gábor; Pickard, Christopher

doi:10.1039/c8fd00034d

Cited by 83 publications

(106 citation statements)

References 76 publications

(77 reference statements)

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Comparison of different atomistic ML potentials (presented in section 2.3.3.1) was studied for water interactions [421]. Gaussian approximation potentials (GAPs) have been extensively used to study different systems, such as elemental boron [422], amorphous carbon [423,424], silicon [425], thermal properties of amorphous GeTe and carbon [426], thermomechanics and defects of iron [427], prediction structures of inorganic crystals by combing ML with random search [428], λ-SOAP method for tensorial properties of atomistic systems [247], and a unified framework to predict the properties of materials and molecules such as silicon, organic molecules and proteins ligands [429]. A recent review of applications of high-dimensional neural neural network potentials [430] summarized the notable number of molecular and materials systems studied, which ranges from simple semiconductors such as silicon [233,431,432] and ZnO [433], to more complex systems such as water and metallic clusters [434], molecules [435][436][437], surfaces [438,439], and liquid/solid interfaces [414,440].…”

Section: Discovery Energies and Stabilitymentioning

confidence: 99%

From DFT to machine learning: recent approaches to materials science–a review

et al. 2019

View full text Add to dashboard Cite

Recent advances in experimental and computational methods are increasing the quantity and complexity of generated data. This massive amount of raw data needs to be stored and interpreted in order to advance the materials science field. Identifying correlations and patterns from large amounts of complex data is being performed by machine learning algorithms for decades. Recently, the materials science community started to invest in these methodologies to extract knowledge and insights from the accumulated data. This review follows a logical sequence starting from density functional theory as the representative instance of electronic structure methods, to the subsequent high-throughput approach, used to generate large amounts of data. Ultimately, data-driven strategies which include data mining, screening, and machine learning techniques, employ the data generated. We show how these approaches to modern computational materials science are being used to uncover complexities and design novel materials with enhanced properties. Finally, we point to the present research problems, challenges, and potential future perspectives of this new exciting field. characterized by its diverse and huge volume, usually ranging from terabytes to petabytes of data, being created in or near real-time. Such data is found either structured and unstructured in nature, and is exhaustive, usually aiming to capture entire populations in a scalable manner [7]. Simple tasks represent challenges in this scale: capture, curation, storage, search, sharing, analysis, and visualization of the data cannot be accomplished without the proper tools. Thus, it can be effectively summarized by the popular 'five V's': volume, velocity, variety, veracity, and value, shown in figure 3(right). A related sixth V is visualization, although not exclusive to Big Data, which requires different techniques to handle data with various characteristics.Striving to tackle the challenges imposed by Big Data, the field of Data Science has arisen. It is largely interdisciplinary being a combination of mathematics and statistics, computer science and programming, and domain knowledge for problem definition and solving, as shown in figure 3(left). Its objective is, roughly speaking, to deal with the whole process of data production, cleaning, preparation, and finally, analysis. Data science encompasses areas such as Big Data, which deals with large volumes of data, and data mining, which relates to analysis processes to discover patterns and extract knowledge from data, part of the so-called Knowledge Discovery in Databases (KDD).The analysis process within Data Science is challenging, as the techniques are very different from traditional static and rigid datasets, generated and analyzed under a predetermined hypothesis. The distinction from traditional data is based on the larger abundance, exhaustivity, and variety of Big Data. It is also much more dynamic, messy and uncertain, being highly relational [7]. Recently, the possibility of overcoming such a challenge slowly sta...

show abstract

Section: Discovery Energies and Stabilitymentioning

confidence: 99%

From DFT to machine learning: recent approaches to materials science–a review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…This iterative training approach was suggested early on already, in the creation of the first ML potentials for silicon, [40] sodium, [41] and for the phase-change material GeTe, [42] the latter of which we will discuss in Section 4.1. [46,[48][49][50] Such approaches hold the long-term promise of discovering new materials on larger length scales than would be accessible to current state-of-the-art methods. [43] A more pressing challenge concerns the sampling of general PESs, which is needed to ensure wide applicability of ML potentials-combining robustness and flexibility in the high-energy regions with sufficient accuracy in the low-energy regions (that is, for the stable and metastable crystal structures).…”

Section: Ingredient 1: Reference Databasesmentioning

confidence: 99%

“…Similar strategies were later used for amorphous carbon, [43] where hundreds of small structural snapshots could be generated in parallel runs using a computationally cheap interim potential, and the end points of these trajectories were evaluated with DFT and added to the database. [5,49] A recently proposed strategy is to explore the PES using global searches [44][45][46][47] that are normally done in DFT-based crystalstructure prediction.…”

Section: Ingredient 1: Reference Databasesmentioning

confidence: 99%

“…[5] This idea can be taken a step further, by exploring and fitting structural space on the fly (and running all structural optimizations with interim potentials, requiring DFT only for single-point input data), thereby unifying ideas from ML potential fitting and crystal-structure searching. [46,[48][49][50] Such approaches hold the long-term promise of discovering new materials on larger length scales than would be accessible to current state-of-the-art methods. [5,49]…”

Section: Ingredient 1: Reference Databasesmentioning

confidence: 99%

“…[46,[48][49][50] Such approaches hold the long-term promise of discovering new materials on larger length scales than would be accessible to current state-of-the-art methods. [5,49]…”

Section: Ingredient 1: Reference Databasesmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

2019

Self Cite

View full text Add to dashboard Cite

In pursuit of this goal, atomic-scale computer simulations have long been a central approach, and two major families of methods are routinely used today. On the one hand, there are quantum-mechanical simulations, in which we solve Schrödinger's equation for the electronic structure of molecular and periodic systems, most widely based on density-functional theory (DFT). [6][7][8] These methods provide (largely) reliable results for structural models of materials that normally contain a few tens or hundreds of atoms. State-of-the-art DFT methods can be applied to many material classes, and they are increasingly used for high-throughput screening and "in silico" (computer-based) design of materials: new compositions and previously unknown structures have been identified in DFT searches and subsequently experimentally realized. [5,[9][10][11] On the other hand, interatomic potential models ("force fields"), parameterizing interactions between atoms with (relatively) simple functional forms, are widely used in materials science to describe matter in molecular dynamics (MD) simulations. These simulations grant access to larger time and length scales, reaching system sizes of up to hundreds of thousands of atoms. [12] In parameterizing these potentials, a certain physical form of the atomic interactions is assumed, often in terms of bond distances, angles, and so on, and physical properties such as equilibrium lattice parameters or elastic constants enter the fitting of the potential. For this reason, such potentials are often called "empirical." They are several orders of magnitude faster than DFT, but necessarily less accurate and less easily transferable.In this Progress Report, we highlight recent developments in "machine-learned" interatomic potentials, which represent a rapidly growing field that promises to do away with the aforementioned trade-offs. Over the last year, there has been a surge of interest in machine learning (ML) methodology: part of it is due to the dramatic growth of ML throughout the scientific disciplines, and part of it is due to tangible success stories of ML-based interatomic potentials that are now beginning to emerge. We will argue that this is an exciting development with very practical implications, currently on the verge of moving from a somewhat specialized new technology to everyday applicability, poised to enhance and complement the communities' existing strengths in computational materials modeling. We will show selected applications of ML potentials to problems in materials science, discuss the current limitations (and possible pitfalls), and outline what we expect to be interesting directions for the development of the field in the coming years.Atomic-scale modeling and understanding of materials have made remarkable progress, but they are still fundamentally limited by the large computational cost of explicit electronic-structure methods such as density-functional theory. This Progress Report shows how machine learning (ML) is currently enabling a new degree of realism in materi...

show abstract

Cluster Fragments in Amorphous Phosphorus and their Evolution under Pressure

2021

Self Cite

View full text Add to dashboard Cite

such as "ab initio" molecular dynamics (AIMD). ML-based interatomic potentials, therefore, are beginning to be applied to a range of challenging materials-science research questions, such as the modeling of phase-change memory materials, [12][13][14] catalysts, [15] or battery materials. [16] Recently, a number of "general-purpose" ML potentials have been reported, which can accurately describe a broad range of atomic configurations and materials properties-including silicon, [17] carbon, [18] aluminum, [19,20] and the binary Ga-As system. [21] The hope for such potentials is to enable "off-the-shelf" use without further modification: for example, the aforementioned silicon ML potential has been used to study complex structural transitions under pressure [22] or unusual mechanical properties of amorphous silicon (a-Si). [23] The starting point for the present study is a general-purpose Gaussian approximation potential (GAP) ML model for bulk and nanostructured phosphorus-which was shown to be flexible enough to be applicable to the pressure-induced liquidliquid phase transition from the molecular fluid to the network liquid, whilst also accurately describing the crystalline allotropes and the layered structure of phosphorene. [24] This GAP is now set to facilitate even more challenging studies on more extended length or time scales, and the exploration of other structurally complex phases for which it has not been explicitly "trained", such as amorphous phosphorus (a-P).Research interest in a-P has grown because of emerging applications in batteries. [25][26][27][28] As a commercially available anode material, red phosphorus provides a large cation-storage ability with high theoretical capacities by forming binary X-P compounds (X = Li, Na, K), but it suffers from low conductivity and a large volumetric change during cycling. [29] As discussed in ref. [30], these issues can be ameliorated by creating composites of a-P and carbonaceous materials: on the one hand, increasing electronic conductivity; [31,32] on the other hand, minimizing the mechanical stress induced by volume changes. [30,33] The structure and properties of phosphorus itself are clearly important for battery applications: for example, experimental work showed that the size of a-P particles in phosphoruscarbon composite anodes has an effect on the electrochemical performance, [34] and in situ transmission electron microscopy (TEM) revealed images of red phosphorus segments within a carbon nanofiber. [35] Computationally, structurally ordered phases have been studied with density-functional theory (DFT; Amorphous phosphorus (a-P) has long attracted interest because of its complex atomic structure, and more recently as an anode material for batteries. However, accurately describing and understanding a-P at the atomistic level remains a challenge. Here, it is shown that large-scale molecular-dynamics simulations, enabled by a machine-learning (ML)-based interatomic potential for phosphorus, can give new insights into the atomic structure of a-P and how...

show abstract

Data-driven learning and prediction of inorganic crystal structures

Cited by 83 publications

References 76 publications

From DFT to machine learning: recent approaches to materials science–a review

From DFT to machine learning: recent approaches to materials science–a review

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Cluster Fragments in Amorphous Phosphorus and their Evolution under Pressure

Contact Info

Product

Resources

About