arXiv subjects

Luca M. Ghiringhelli

Publications and source records attributed to Luca M. Ghiringhelli.

At least 37 records · Page 2Linked to original sources

arXiv2021

Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning

Due to their ability to recognize complex patterns, neural networks can drive a paradigm shift in the analysis of materials science data. Here, we introduce ARISE, a crystal-structure identification method based on Bayesian deep learning. As a major step forward, ARISE is robust to structural noise and can treat more than 100 crystal structures, a number that can be extended on demand. While being trained on ideal structures only, ARISE correctly characterizes strongly perturbed single- and polycrystalline systems, from both synthetic and experimental resources. The probabilistic nature of the Bayesian-deep-learning model allows to obtain principled uncertainty estimates, which are found to be correlated with crystalline order of metallic nanoparticles in electron tomography experiments. Applying unsupervised learning to the internal neural-network representations reveals grain boundaries and (unapparent) structural regions sharing easily interpretable geometrical properties. This work enables the hitherto hindered analysis of noisy atomic structural data from computations or experiments.

cond-mat.mtrl-sci↗

arXiv2021

Trends in atomistic simulation software usage

Driven by the unprecedented computational power available to scientific research, the use of computers in solid-state physics, chemistry and materials science has been on a continuous rise. This review focuses on the software used for the simulation of matter at the atomic scale. We provide a comprehensive overview of major codes in the field, and analyze how citations to these codes in the academic literature have evolved since 2010. An interactive version of the underlying data set is available at https://atomistic.software .

cond-mat.mtrl-sci↗

arXiv2021

Data-driven equation for drug-membrane permeability across drugs and membranes

Drug efficacy depends on its capacity to permeate across the cell membrane. We consider the prediction of passive drug-membrane permeability coefficients. Beyond the widely recognized correlation with hydrophobicity, we additionally consider the functional relationship between passive permeation and acidity. To discover easily interpretable equations that explain the data well, we use the recently proposed sure-independence screening and sparsifying operator (SISSO), an artificial-intelligence technique that combines symbolic regression with compressed sensing. Our study is based on a large in silico dataset of 0.4 million small molecules extracted from coarse-grained simulations. We rationalize the equation suggested by SISSO via an analysis of the inhomogeneous solubility-diffusion model in several asymptotic acidity regimes. We further extend our analysis to the dependence on lipid-membrane composition. Lipid-tail unsaturation plays a key role, but surprisingly contributes stepwise rather than proportionally. Our results are in line with previously observed changes in permeability, suggesting the distinction between liquid-disordered (Ld) and liquid-ordered (Lo) permeation. Together, compressed sensing with analytically derived asymptotes establish and validate an accurate, broadly applicable, and interpretable equation for passive permeability across both drug and lipid-tail chemistry.

physics.chem-ph↗

arXiv2021

Identifying outstanding transition-metal-alloy heterogeneous catalysts for the oxygen reduction and evolution reactions via subgroup discovery

In order to estimate the reactivity of a large number of potentially complex heterogeneous catalysts while searching for novel and more efficient materials, physical as well as data-centric models have been developed for a faster evaluation of adsorption energies compared to first-principles calculations. However, global models designed to describe as many materials as possible might overlook the very few compounds that have the appropriate adsorption properties to be suitable for a given catalytic process. Here, the subgroup-discovery (SGD) local artificial-intelligence approach is used to identify the key descriptive parameters and constrains on their values, the so-called SG rules, which particularly describe transition-metal surfaces with outstanding adsorption properties for the oxygen reduction and evolution reactions. We start from a data set of 95 oxygen adsorption energy values evaluated by density-functional-theory calculations for several monometallic surfaces along with 16 atomic, bulk and surface properties as candidate descriptive parameters. From this data set, SGD identifies constraints on the most relevant parameters describing materials and adsorption sites that (i) result in O adsorption energies within the Sabatier-optimal range required for the oxygen reduction reaction and (ii) present the largest deviations from the linear scaling relations between O and OH adsorption energies, which limit the performance in the oxygen evolution reaction. The SG rules not only reflect the local underlying physicochemical phenomena that result in the desired adsorption properties but also guide the challenging design of alloy catalysts.

cond-mat.mtrl-sci↗

arXiv2021

Interpretability of machine-learning models in physical sciences

In machine learning (ML), it is in general challenging to provide a detailed explanation on how a trained model arrives at its prediction. Thus, usually we are left with a black-box, which from a scientific standpoint is not satisfactory. Even though numerous methods have been recently proposed to interpret ML models, somewhat surprisingly, interpretability in ML is far from being a consensual concept, with diverse and sometimes contrasting motivations for it. Reasonable candidate properties of interpretable models could be model transparency (i.e. how does the model work?) and post hoc explanations (i.e., what else can the model tell me?). Here, I review the current debate on ML interpretability and identify key challenges that are specific to ML applied to materials science.

cond-mat.mtrl-sci↗

arXiv2021

Materials genes of heterogeneous catalysis from clean experiments and artificial intelligence

Heterogeneous catalysis is an example of a complex materials function, governed by an intricate interplay of several processes, e.g., the different surface chemical reactions, and the dynamic re-structuring of the catalyst material at reaction conditions. Modelling the full catalytic progression via first-principles statistical mechanics is impractical, if not impossible. Instead, we show here how a tailored artificial-intelligence approach can be applied, even to a small number of materials, to model catalysis and determine the key descriptive parameters ("materials genes") reflecting the processes that trigger, facilitate, or hinder catalyst performance. We start from a consistent experimental set of "clean data", containing nine vanadium-based oxidation catalysts. These materials were synthesized, fully characterized, and tested according to standardized protocols. By applying the symbolic-regression SISSO approach, we identify correlations between the few most relevant materials properties and their reactivity. This approach highlights the underlying physicochemical processes, and accelerates catalyst design.

cond-mat.mtrl-sci↗

arXiv2020

Artificial Intelligence for High-Throughput Discovery of Topological Insulators: the Example of Alloyed Tetradymites

Significant advances have been made in predicting new topological materials using high-throughput empirical descriptors or symmetry-based indicators. To date, these approaches have been applied to materials in existing databases, and are severely limited to systems with well-defined symmetries, leaving a much larger materials space unexplored. Using tetradymites as a prototypical class of examples, we uncover a novel two-dimensional descriptor by applying an artificial intelligence (AI) based approach for fast and reliable identification of the topological characters of a drastically expanded range of materials, without prior determination of their specific symmetries and detailed band structures. By leveraging this descriptor that contains only the atomic number and electronegativity of the constituent species, we have readily scanned a huge number of alloys in the tetradymite family. Strikingly, nearly half of which are identified to be topological insulators, revealing a much larger territory of the topological materials world. The present work also attests the increasingly important role of such AI-based approaches in modern materials discovery.

cond-mat.mtrl-sci↗

arXiv2019

Determining Surface Phase Diagrams Including Anharmonic Effects

We introduce a massively parallel replica-exchange grand-canonical sampling algorithm to simulate materials at realistic conditions, in particular surfaces and clusters in reactive atmospheres. Its purpose is to determine in an automated fashion equilibrium phase diagrams for a given potential-energy surface (PES) and for any observable sampled in the grand-canonical ensemble. The approach enables an unbiased sampling of the phase space and is embarrassingly parallel. It is demonstrated for a model of Lennard-Jones system describing a surface in contact with a gas phase. Furthermore, the algorithm is applied to Si$_M$ clusters ($M=2, 4$) in contact with an H$_{2}$ atmosphere, with all interactions described at the \textit{ab initio} level, i.e., via density-functional theory, with the PBE gradient-corrected exchange-correlation functional. We identify the most thermodynamically stable phases at finite $T, p$(H$_{2}$) conditions.

cond-mat.mtrl-sci↗

arXiv2019

New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides

Predicting the stability of the perovskite structure remains a longstanding challenge for the discovery of new functional materials for many applications including photovoltaics and electrocatalysts. We developed an accurate, physically interpretable, and one-dimensional tolerance factor, τ, that correctly predicts 92% of compounds as perovskite or nonperovskite for an experimental dataset of 576 $ABX_3$ materials ($\textit{X} =$ $O^{2-}$, $F^-$, $Cl^-$, $Br^-$, $I^-$) using a novel data analytics approach based on SISSO (sure independence screening and sparsifying operator). τ is shown to generalize outside the training set for 1,034 experimentally realized single and double perovskites (91% accuracy) and is applied to identify 23,314 new double perovskites ($A_2$$\textit{BB'}$$X_6$) ranked by their probability of being stable as perovskite. This work guides experimentalists and theorists towards which perovskites are most likely to be successfully synthesized and demonstrates an approach to descriptor identification that can be extended to arbitrary applications beyond perovskite stability predictions.

cond-mat.mtrl-sci↗

arXiv2019

Simultaneous Learning of Several Materials Properties from Incomplete Databases with Multi-Task SISSO

The identification of descriptors of materials properties and functions that capture the underlying physical mechanisms is a critical goal in data-driven materials science. Only such descriptors will enable a trustful and efficient scanning of materials spaces and possibly the discovery of new materials. Recently, the sure-independence screening and sparsifying operator (SISSO) has been introduced and was successfully applied to a number of materials-science problems. SISSO is a compressed-sensing based methodology yielding predictive models that are expressed in form of analytical formulas, built from simple physical properties. These formulas are systematically selected from an immense number (billions or more) of candidates. In this work, we describe a powerful extension of the methodology to a 'multi-task learning' approach, which identifies a single descriptor capturing multiple target materials properties at the same time. This approach is specifically suited for a heterogeneous materials database with scarce or partial data, e.g., in which not all properties are reported for all materials in the training set. As showcase examples, we address the construction of materials-properties maps for the relative stability of octet-binary compounds, considering several crystal phases simultaneously, and the metal/insulator classification of binary materials distributed over many crystal-prototypes.

cond-mat.mtrl-sci↗

arXiv2018

NOMAD 2018 Kaggle Competition: Solving Materials Science Challenges Through Crowd Sourcing

Machine learning (ML) is increasingly used in the field of materials science, where statistical estimates of computed properties are employed to rapidly examine the chemical space for new compounds. However, a systematic comparison of several ML models for this domain has been hindered by the scarcity of appropriate datasets of materials properties, as well as the lack of thorough benchmarking studies. To address this, a public data-analytics competition was organized by the Novel Materials Discovery (NOMAD) Centre of Excellence and hosted by the on-line platform Kaggle using a dataset of $3\,000$ (Al$_x$ Ga$_y$ In$_z$)$_2$ O$_3$ compounds (with $x+y+z = 1$). The aim of this challenge was to identify the best ML model for the prediction of two key physical properties that are relevant for optoelectronic applications: the electronic band gap energy and the crystalline formation energy. In this contribution, we present a summary of the top three ML approaches of the competition including the 1st place solution based on a crystal graph representation that is new for ML of the properties of materials. The 2nd place model combined many candidate descriptors from a set of compositional, atomic environment-based, and average structural properties with the light gradient-boosting machine regression model. The 3rd place model employed the smooth overlap of atomic positions representation with a neural network. To gain insight into whether the representation or the regression model determines the overall model performance, nine ML models obtained by combining the representations and regression models of the top three approaches were compared by looking at the correlations among prediction errors. At fixed representation, the largest correlation is observed in predictions made with kernel ridge regression and neural network, reflecting a similar performance on the same test set samples.

cond-mat.mtrl-sci↗

arXiv2018

Two-to-three dimensional transition in neutral gold clusters: the crucial role of van der Waals interactions and temperature

We predict the structures of neutral gas-phase gold clusters ($Au_n$, $n$ = 5$-$13) at finite temperatures based on free-energy calculations obtained by replica-exchange ab initio molecular dynamics. The structures of neutral $Au_5$$-$$Au_{13}$ clusters are assigned at 100 K based on a comparison of experimental far-infrared multiple photon dissociation spectra performed on Kr-tagged gold clusters with theoretical anharmonic IR spectra and free-energy calculations. The critical gold cluster size where the most stable isomer changes from planar to nonplanar is $Au_{11}$ (capped-trigonal prism, $D_{3h}$) at 100 K. However, at 300 K (i.e., room temperature), planar and nonplanar isomers may coexist even for $Au_8$, $Au_9$, and $Au_{10}$ clusters. Density-functional theory exchange-correlation functionals within the generalized gradient or hybrid approximation must be corrected for long-range van der Waals interactions to accurately predict relative gold cluster isomer stabilities. Our work gives insight into the stable structures of gas-phase gold clusters by highlighting the impact of temperature, and therefore the importance of free-energy over total energy studies, and long-range van der Waals interactions on gold cluster stability.

cond-mat.mtrl-sci↗

arXiv2018

(Meta-)stability and Core-Shell Dynamics of Gold Nanoclusters at Finite Temperature

Gold nanoclusters have been the focus of numerous computational studies but an atomistic understanding of their structural and dynamical properties at finite temperature is far from satisfactory. To address this deficiency, we investigate gold nanoclusters via ab initio molecular dynamics, in a range of sizes where a core-shell morphology is observed. We analyze their structure and dynamics using of state-of-the-art techniques, including unsupervised machine-learning nonlinear dimensionality reduction (sketch-map) for describing the similarities and differences among the range of sampled configurations. We find that, whereas the gold nanoclusters exhibit continuous structural rearrangement, they clearly show persistent motifs: a cationic core of one to five atoms is loosely bound to a shell which typically displays a substructure resulting from the competition between locally spherical vs planar fragments. Besides illuminating the properties of core-shell gold nanoclusters, the present study proposes a set of useful tools for understanding their nature in operando.

cond-mat.mes-hall↗

arXiv2018

SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates

The lack of reliable methods for identifying descriptors - the sets of parameters capturing the underlying mechanisms of a materials property - is one of the key factors hindering efficient materials development. Here, we propose a systematic approach for discovering descriptors for materials properties, within the framework of compressed-sensing based dimensionality reduction. SISSO (sure independence screening and sparsifying operator) tackles immense and correlated features spaces, and converges to the optimal solution from a combination of features relevant to the materials' property of interest. In addition, SISSO gives stable results also with small training sets. The methodology is benchmarked with the quantitative prediction of the ground-state enthalpies of octet binary materials (using ab initio data) and applied to the showcase example of predicting the metal/insulator classification of binaries (with experimental data). Accurate, predictive models are found in both cases. For the metal-insulator classification model, the predictive capability are tested beyond the training data: It rediscovers the available pressure-induced insulator->metal transitions and it allows for the prediction of yet unknown transition candidates, ripe for experimental validation. As a step forward with respect to previous model-identification methods, SISSO can become an effective tool for automatic materials development.

cond-mat.mtrl-sci↗

arXiv2018

Analysis of Topological Transitions in Two-dimensional Materials by Compressed Sensing

Quantum spin-Hall insulators (QSHIs), i.e., two-dimensional topological insulators (TIs) with a symmetry-protected band inversion, have attracted considerable scientific interest in recent years. In this work, we have computed the topological Z2 invariant for 220 functionalized honeycomb lattices that are isoelectronic to functionalized graphene. Besides confirming the TI character of well-known materials such as functionalized stanene, our study identifies 45 yet unreported QSHIs. We applied a compressed-sensing approach to identify a physically meaningful descriptor for the Z2 invariant that only depends on the properties of the material's constituent atoms. This enables us to draw a map of materials, in which metals, trivial insulators, and QSHI form distinct regions. This analysis yields fundamental insights in the mechanisms driving topological transitions. The transferability of the identified model is explicitly demonstrated for an additional set of honeycomb lattices with different functionalizations that are not part of the original set of 220 graphene-type materials used to identify the descriptor. In this class, we predict 74 more novel QSHIs that have not been reported in literature yet.

cond-mat.mtrl-sci↗

arXiv2018

Structure and electronic properties of transition-metal/Mg bimetallic clusters at realistic temperatures and oxygen partial pressures

Composition, atomic structure, and electronic properties of TM$_x$Mg$_y$O$_z$ clusters (TM = Cr, Ni, Fe, Co, $x+y \leq 3$) at realistic temperature $T$ and partial oxygen pressure $p_{\textrm{O}_2}$ conditions are explored using the {\em ab initio} atomistic thermodynamics approach. The low-energy isomers of the different clusters are identified using a massively parallel cascade genetic algorithm at the hybrid density-functional level of theory. On analyzing a large set of data, we find that the fundamental gap E$_\textrm{g}$ of the thermodynamically stable clusters are strongly affected by the presence of Mg-coordinated O$_2$ moieties. In contrast, the nature of the transition metal does not play a significant role in determining E$_\textrm{g}$. Using E$_\textrm{g}$ of a cluster as a descriptor of its redox properties, our finding is against the conventional belief that the transition metal plays the key role in determining the electronic and therefore chemical properties of the clusters. High reactivity may be correlated more strongly with oxygen content in the cluster than with any specific TM type.

cond-mat.mtrl-sci↗

arXiv2018

GAtor: A First Principles Genetic Algorithm for Molecular Crystal Structure Prediction

We present the implementation of GAtor, a massively parallel, first principles genetic algorithm (GA) for molecular crystal structure prediction. GAtor is written in Python and currently interfaces with the FHI-aims code to perform local optimizations and energy evaluations using dispersion-inclusive density functional theory (DFT). GAtor offers a variety of fitness evaluation, selection, crossover, and mutation schemes. Breeding operators designed specifically for molecular crystals provide a balance between exploration and exploitation. Evolutionary niching is implemented in GAtor by using machine learning to cluster the dynamically updated population by structural similarity and then employing a cluster-based fitness function. Evolutionary niching promotes uniform sampling of the potential energy surface by evolving several sub-populations, which helps overcome initial pool biases and selection biases (genetic drift). The various settings offered by GAtor increase the likelihood of locating numerous low-energy minima, including those located in disconnected, hard to reach regions of the potential energy landscape. The best structures generated are re-relaxed and re-ranked using a hierarchy of increasingly accurate DFT functionals and dispersion methods. GAtor is applied to a chemically diverse set of four past blind test targets, characterized by different types of intermolecular interactions. The experimentally observed structures and other low-energy structures are found for all four targets. In particular, for Target II, 5-cyano-3-hydroxythiophene, the top ranked putative crystal structure is a $Z^\prime$=2 structure with P$\bar{1}$ symmetry and a scaffold packing motif, which has not been reported previously.

cond-mat.mtrl-sci↗

arXiv2017

Theoretical evidence for unexpected O-rich phases at corners of MgO surfaces

Realistic oxide materials are often semiconductors, in particular at elevated temperatures, and their surfaces contain undercoordiated atoms at structural defects such as steps and corners. Using hybrid density-functional theory and ab initio atomistic thermodynamics, we investigate the interplay of bond-making, bond-breaking, and charge-carrier trapping at the corner defects at the (100) surface of a p-doped MgO in thermodynamic equilibrium with an O2 atmosphere. We show that by manipulating the coordination of surface atoms one can drastically change and even reverse the order of stability of reduced versus oxidized surface sites.

cond-mat.mtrl-sci↗