Recent advances and applications of machine learning in solid-state materials science

Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana; Marques, Miguel A. L.

doi:10.1038/s41524-019-0221-0

Cited by 1,708 publications

(1,220 citation statements)

References 443 publications

Supporting

Mentioning

1,108

Contrasting

Unclassified

Order By: Relevance

“…Here, we will provide a noncomprehensive enumeration and summary of common ML models necessary to understand their application in various energy materials problems; readers interested in a more comprehensive treatise on the topic are pointed to several excellent textbooks and recent reviews …”

Section: Model Selection and Trainingmentioning

confidence: 99%

A Critical Review of Machine Learning of Energy Materials

Chen

Zuo

et al. 2020

Advanced Energy Materials

395

281

View full text Add to dashboard Cite

Machine learning (ML) is rapidly revolutionizing many fields and is starting to change landscapes for physics and chemistry. With its ability to solve complex tasks autonomously, ML is being exploited as a radically new way to help find material correlations, understand materials chemistry, and accelerate the discovery of materials. Here, an in‐depth review of the application of ML to energy materials, including rechargeable alkali‐ion batteries, photovoltaics, catalysts, thermoelectrics, piezoelectrics, and superconductors, is presented. A conceptual framework is first provided for ML in materials science, with a broad overview of different ML techniques as well as best practices. This is followed by a critical discussion of how ML is applied in energy materials. This review is concluded with the perspectives on major challenges and opportunities in this exciting field.

show abstract

Section: Model Selection and Trainingmentioning

confidence: 99%

A Critical Review of Machine Learning of Energy Materials

Chen

Zuo

et al. 2020

Advanced Energy Materials

395

281

View full text Add to dashboard Cite

show abstract

“…In recent years, the astonishing advances in machine-learning techniques have opened new possibilities to address critical challenges in various fields, also in materials science [9,[34][35][36][37][38]. For example, actively trained machine-learning interatomic potentials [39] have been successfully employed to predict novel materials [40,41] and examine lattice dynamics [42] and thermal conductivity [43] of bulk materials.…”

Section: Introductionmentioning

confidence: 99%

Efficient machine-learning based interatomic potentialsfor exploring thermal conductivity in two-dimensional materials

et al. 2020

View full text Add to dashboard Cite

It is well-known that the calculation of thermal conductivity using classical molecular dynamics (MD) simulations strongly depends on the choice of the appropriate interatomic potentials. As proven for the case of graphene, while most of the available interatomic potentials estimate the structural and elastic constants with high accuracy, when employed to predict the lattice thermal conductivity they however lead to a variation of predictions by one order of magnitude. Here we present our results on using machine-learning interatomic potentials (MLIPs) passively fitted to computationally inexpensive ab-initio molecular dynamics trajectories without any tuning or optimizing of hyperparameters. These first-attempt potentials could reproduce the phononic properties of different two-dimensional (2D) materials obtained using density functional theory (DFT) simulations. To illustrate the efficiency of the trained MLIPs, we consider polyaniline C 3 N nanosheets. C 3 N monolayer was selected because the classical MD and different first-principles results contradict each other, resulting in a scientific dilemma. It is shown that the predicted thermal conductivity of 418 ± 20 W mK −1 for C 3 N monolayer by the non-equilibrium MD simulations on the basis of a first-attempt MLIP evidences an improved accuracy when compared with the commonly employed MD models. Moreover, MLIP-based prediction can be considered as a solution to the debated reports in the literature. This study highlights that passively fitted MLIPs can be effectively employed as versatile and efficient tools to obtain accurate estimations of thermal conductivities of complex materials using classical MD simulations. In response to remarkable growth of 2D materials family, the devised modeling methodology could play a fundamental role to predict the thermal conductivity.

show abstract

“…Taking into account that the samples come from six different localities it turns out that the capacity of the models to predict provenance is computed using only a very few test samples per site (for instance in the case of La Bisbal 9 test samples were used, and for Quart, only four). It is known that the success of machine learning methods depends on the amount and quality of available data [44] and a minimum total dataset size of 100 samples has been hypothesized as the lower limit to apply machine learning methods in materials research [45]. The presented results have been derived with a dataset of 208 (just above double the hypothesized minimum size), therefore an enlarged dataset would be required to increase the confidence on the obtained accuracy.…”

Section: Discussionmentioning

confidence: 99%

Application of Supervised Machine-Learning Methods for Attesting Provenance in Catalan Traditional Pottery Industry

Anglisano

Casas

Anglisano³

et al. 2019

Minerals

View full text Add to dashboard Cite

The traditional pottery industry was an important activity in Catalonia (NE Spain) up to the 20th century. However, nowadays only few workshops persist in small villages were the activity is promoted as a touristic attraction. The preservation and promotion of traditional pottery in Catalonia is part of an ongoing strategy of tourism diversification that is revitalizing the sector. The production of authenticable local pottery handicrafts aims at attracting cultivated and high-purchasing power tourists. The present paper inspects several approaches to set up a scientific protocol based on the chemical composition of both raw materials and pottery. These could be used to develop a seal of quality and provenance to regulate the sector. Six Catalan villages with a renowned tradition of local pottery production have been selected. The chemical composition of their clays and the corresponding fired products has been obtained by Energy dispersive X-ray fluorescence (EDXRF). Using the obtained geochemical dataset, a number of unsupervised and supervised machine learning methods have been applied to test their applicability to define geochemical fingerprints that could allow inter-site discrimination. The unsupervised approach fails to distinguish samples from different provenances. These methods are only roughly able to divide the different provenances in two large groups defined by their different SiO 2 and CaCO 3 concentrations. In contrast, almost all the tested supervised methods allow inter-site discrimination with accuracy levels above 80%, and accuracies above 85% were obtained using a meta-model combining all the predictive supervised methods. The obtained results can be taken as encouraging and demonstrative of the potential of the supervised approach as a way to define geochemical fingerprints to track or attest the provenance of samples.

show abstract

Recent advances and applications of machine learning in solid-state materials science

Cited by 1,708 publications

References 443 publications

A Critical Review of Machine Learning of Energy Materials

A Critical Review of Machine Learning of Energy Materials

Efficient machine-learning based interatomic potentialsfor exploring thermal conductivity in two-dimensional materials

Application of Supervised Machine-Learning Methods for Attesting Provenance in Catalan Traditional Pottery Industry

Contact Info

Product

Resources

About