Accelerated Discovery of Efficient Solar-cell Materials using Quantum and Machine-learning Methods

When Machine Learning Meets 2D Materials: A Review

The availability of an ever-expanding portfolio of 2D materials with rich internal degrees of freedom (spin, excitonic, valley, sublattice, and layer pseudospin) together with the unique ability to tailor heterostructures made layer by layer in a precisely chosen stacking sequence and relative crystallographic alignments, offers an unprecedented platform for realizing materials by design. However, the breadth of multi-dimensional parameter space and massive data sets involved is emblematic of complex, resource-intensive experimentation, which not only challenges the current state of the art but also renders exhaustive sampling untenable. To this end, machine learning, a very powerful data-driven approach and subset of artificial intelligence, is a potential game-changer, enabling a cheaper - yet more efficient - alternative to traditional computational strategies. It is also a new paradigm for autonomous experimentation for accelerated discovery and machine-assisted design of functional 2D materials and heterostructures. Here, the study reviews the recent progress and challenges of such endeavors, and highlight various emerging opportunities in this frontier research area.

A Perspective on Sustainable Computational Chemistry Software Development and Integration

The power of quantum chemistry to predict the ground and excited state properties of complex chemical systems has driven the development of computational quantum chemistry software, integrating advances in theory, applied mathematics, and computer science. The emergence of new computational paradigms associated with exascale technologies also poses significant challenges that require a flexible forward strategy to take full advantage of existing and forthcoming computational resources. In this context, the sustainability and interoperability of computational chemistry software development are among the most pressing issues. In this perspective, we discuss software infrastructure needs and investments with an eye to fully utilize exascale resources and provide unique computational tools for next-generation science problems and scientific discoveries.

Accurate, interpretable predictions of materials properties within transformer language models

Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability. Here, we present an elegant way to make their reasoning transparent. Human-readable text-based descriptions automatically generated within a suite of open-source tools are proposed as materials representation. Transformer language models pretrained on 2 million peer-reviewed articles take as input well-known terms such as chemical composition, crystal symmetry, and site geometry. Our approach outperforms crystal graph networks by classifying four out of five analyzed properties if one considers all available reference data. Moreover, fine-tuned text-based models show high accuracy in the ultra-small data limit. Explanations of their internal machinery are produced using local interpretability techniques and are faithful and consistent with domain expert rationales. This language-centric framework makes accurate property predictions accessible to people without artificial-intelligence expertise.

Inverse Design of Next-Generation Superconductors Using Data-Driven Deep Generative Models

Finding new superconductors with a high critical temperature (T_c) has been a challenging task due to computational and experimental costs. We present a diffusion model inspired by the computer vision community to generate new superconductors with unique structures and chemical compositions. Specifically, we used a crystal diffusion variational autoencoder (CDVAE) along with atomistic line graph neural network (ALIGNN) pretrained models and the Joint Automated Repository for Various Integrated Simulations (JARVIS) superconducting database of density functional theory (DFT) calculations to generate new superconductors with a high success rate. We started with a DFT data set of ∼1000 superconducting materials to train the diffusion model. We used the model to generate 3000 new structures, which along with pretrained ALIGNN screening results in 61 candidates. For the top candidates, we performed DFT calculations for validation. Such approaches go beyond funnel-like materials screening approaches and allow for the inverse design of next-generation materials.

High-Throughput DFT-Based Discovery of Next Generation Two-Dimensional (2D) Superconductors

High-throughput density functional theory (DFT) calculations allow for a systematic search for conventional superconductors. With the recent interest in two-dimensional (2D) superconductors, we used a high-throughput workflow to screen over 1000 2D materials in the JARVIS-DFT database and performed electron-phonon coupling calculations, using the McMillan-Allen-Dynes formula to calculate the superconducting transition temperature (T_c) for 165 of them. Of these 165 materials, we identify 34 dynamically stable structures with transition temperatures above 5 K, including materials such as W₂N₃, NbO₂, ZrBrO, TiClO, NaSn₂S₄, Mg₂B₄C₂, and the previously unreported Mg₂B₄N₂ (T_c = 21.8 K). Finally, we performed experiments to determine the T_c of selected layered superconductors (2H-NbSe₂, 2H-NbS₂, ZrSiS, FeSe) and discuss the measured results within the context of our DFT results. We aim that the outcome of this workflow can guide future computational and experimental studies of new and emerging 2D superconductors by providing a roadmap of high-throughput DFT data.

Systematic DFT+U and Quantum Monte Carlo Benchmark of Magnetic Two-Dimensional (2D) CrX3 (X = I, Br, Cl, F)

The search for two-dimensional (2D) magnetic materials has attracted a great deal of attention because of the experimental synthesis of 2D CrI₃, which has a measured Curie temperature of 45 K. Often times, these monolayers have a higher degree of electron correlation and require more sophisticated methods beyond density functional theory (DFT). Diffusion Monte Carlo (DMC) is a correlated electronic structure method that has been demonstrated to be successful for calculating the electronic and magnetic properties of a wide variety of 2D and bulk systems, since it has a weaker dependence on the Hubbard parameter (U) and density functional. In this study, we designed a workflow that combines DFT +U and DMC in order to treat 2D correlated magnetic systems. We chose monolayer CrX₃ (X = I, Br, Cl, F), with a stronger focus on CrI₃ and CrBr₃, as a case study due to the fact that they have been experimentally realized and have a finite critical temperature. With this DFT+U and DMC workflow and the analytical method of Torelli and Olsen, we estimated a maximum value of 43.56 K for the T_c of CrI₃ and 20.78 K for the T_c of CrBr₃, in addition to analyzing the spin densities and magnetic properties with DMC and DFT+U. We expect that running this workflow for a well-known material class will aid in the future discovery and characterization of lesser known and more complex correlated 2D magnetic materials.

Spiers Memorial Lecture: Next generation chalcogenide-based absorbers for thin-film solar cells

Inorganic-based thin-film photovoltaics (TFPV) represents an important component of the growing low-carbon energy market and plays a vital role in the drive toward lower cost and increased penetration of solar energy. Yet, commercialized thin-film absorber technologies suffer from some non-ideal characteristics, such as toxic or non-abundant element use (e.g., CdTe and Cu(In,Ga)(S,Se)₂, which bring into question their suitability for terawatt deployment. Numerous promising chalcogenide, halide, pnictide and oxide semiconductors are being pursued to bridge these concerns for TFPV and several promising paths have emerged, both as prospective replacements for the entrenched technologies, and to serve as partner (i.e., higher bandgap) absorbers for tandem junction devices-e.g., to be used with a lower bandgap Si bottom cell. The current perspective will primarily focus on emerging chalcogenide-based technologies and provide both an overview of absorber candidates that have been of recent interest and a deeper dive into an exemplary Cu₂BaSnS₄-related family. Overall, considering the combined needs of high-performance, low-cost, and operational stability, as well as the experiences gained from existing commercialized thin-film absorber technologies, chalcogenide-based semiconductors represent a promising direction for future PV development and also serve to highlight common themes and needs among the broader TFPV materials family.

Indirect Band Gap Semiconductors for Thin-Film Photovoltaics: High-Throughput Calculation of Phonon-Assisted Absorption

Discovery of high-performance materials remains one of the most active areas in photovoltaics (PV) research. Indirect band gap materials form the largest part of the semiconductor chemical space, but predicting their suitability for PV applications from first-principles calculations remains challenging. Here, we propose a computationally efficient method to account for phonon-assisted absorption across the indirect band gap and use it to screen 127 experimentally known binary semiconductors for their potential as thin-film PV absorbers. Using screening descriptors for absorption, carrier transport, and nonradiative recombination, we identify 28 potential candidate materials. The list, which contains 20 indirect band gap semiconductors, comprises well-established (3), emerging (16), and previously unexplored (9) absorber materials. Most of the new compounds are anion-rich chalcogenides (TiS₃ and Ga₂Te₅) and phosphides (PdP₂, CdP₄, MgP₄, and BaP₃) containing homoelemental bonds and represent a new frontier in PV materials research. Our work highlights the previously underexplored potential of indirect band gap materials for optoelectronic thin-film technologies.

High-Throughput Synthesis of Thin Films for the Discovery of Energy Materials: A Perspective

Thin films are an integral part of many electronic and optoelectronic devices. They also provide an excellent platform for material characterization. Therefore, strategies for the fabrication of thin films are constantly developed and have significantly benefited from the advent of high-throughput synthesis (HTS) platforms. This perspective summarizes recent advances in HTS of thin films from experimentalists’ point of view. The work analyzes general strategies of HTS and then discusses their use in developing new energy materials for applications that rely on thin films, such as solar cells, light-emitting diodes, batteries, superconductors, and thermoelectrics. The perspective also summarizes some key challenges and opportunities in the HTS of thin films.

Quantum machine learning for chemistry and physics

Machine learning (ML) has emerged as a formidable force for identifying hidden but pertinent patterns within a given data set with the objective of subsequent generation of automated predictive behavior. In recent years, it is safe to conclude that ML and its close cousin, deep learning (DL), have ushered in unprecedented developments in all areas of physical sciences, especially chemistry. Not only classical variants of ML, even those trainable on near-term quantum hardwares have been developed with promising outcomes. Such algorithms have revolutionized materials design and performance of photovoltaics, electronic structure calculations of ground and excited states of correlated matter, computation of force-fields and potential energy surfaces informing chemical reaction dynamics, reactivity inspired rational strategies of drug designing and even classification of phases of matter with accurate identification of emergent criticality. In this review we shall explicate a subset of such topics and delineate the contributions made by both classical and quantum computing enhanced machine learning algorithms over the past few years. We shall not only present a brief overview of the well-known techniques but also highlight their learning strategies using statistical physical insight. The objective of the review is not only to foster exposition of the aforesaid techniques but also to empower and promote cross-pollination among future research in all areas of chemistry which can benefit from ML and in turn can potentially accelerate the growth of such algorithms.

Discovery of Lead-Free Perovskites for High-Performance Solar Cells via Machine Learning: Ultrabroadband Absorption, Low Radiative Combination, and Enhanced Thermal Conductivities

Exploring lead-free candidates and improving efficiency and stability remain the obstacle of hybrid organic-inorganic perovskite-based devices commercialization. Traditional trial-and-error methods seriously restrict the discovery especially for large search space, complex crystal structure and multi-objective properties. Here, the authors propose a multi-step and multi-stage screening scheme to accelerate the discovery of hybrid organic-inorganic perovskites A2 BB'X6 from a large number of candidates through combining machine learning with high-throughput calculations for pursuing excellent efficiency and thermal stability in solar cells. Followed by a series of screenings, the structure-property relationships mapping A2 BB'X6 properties are built and the predictions are close to reported experimental results. Successfully, four experimental-feasibly candidates with good stability, high Debye temperature and suitable band gap are screened out and further verified by density-functional theory calculations, in which the predicted efficiency for three lead-free candidates ((CH3 NH3 )2 AgGaBr6 , (CH3 NH3 )2 AgInBr6 and (C2 NH6 )2 AgInBr6 ) achieves 20.6%, 19.9% and 27.6% due to ultrabroadband absorption region ranging from UVC to IRC with excitonic radiative combination rates as low as 10 ps, large or intermediate polarons form with properties similar to CH3 NH3 PbI3 and the calculated thermal conductivities are 5.04, 4.39 and 5.16 Wm-1 K-1 , respectively, with Debye temperatures larger than 500 K, beneficial for suppression of both nonradiative combination and heat-induced degradation.

Scalable estimator of the diversity for de novo molecular generation resulting in a more robust QM dataset (OD9) and a more efficient molecular optimization

Chemical diversity is one of the key term when dealing with machine learning and molecular generation. This is particularly true for quantum chemical datasets. The composition of which should be done meticulously since the calculation is highly time demanding. Previously we have seen that the most known quantum chemical dataset QM9 lacks chemical diversity. As a consequence, ML models trained on QM9 showed generalizability shortcomings. In this paper we would like to present (i) a fast and generic method to evaluate chemical diversity, (ii) a new quantum chemical dataset of 435k molecules, OD9, that includes QM9 and new molecules generated with a diversity objective, (iii) an analysis of the diversity impact on unconstrained and goal-directed molecular generation on the example of QED optimization. Our innovative approach makes it possible to individually estimate the impact of a solution to the diversity of a set, allowing for effective incremental evaluation. In the first application, we will see how the diversity constraint allows us to generate more than a million of molecules that would efficiently complete the reference datasets. The compounds were calculated with DFT thanks to a collaborative effort through the QuChemPedIA@home BOINC project. With regard to goal-directed molecular generation, getting a high QED score is not complicated, but adding a little diversity can cut the number of calls to the evaluation function by a factor of ten.

Database of Wannier tight-binding Hamiltonians using high-throughput density functional theory

Wannier tight-binding Hamiltonians (WTBH) provide a computationally efficient way to predict electronic properties of materials. In this work, we develop a computational workflow for high-throughput Wannierization of density functional theory (DFT) based electronic band structure calculations. We apply this workflow to 1771 materials (1406 3D and 365 2D), and we create a database with the resulting WTBHs. We evaluate the accuracy of the WTBHs by comparing the Wannier band structures to directly calculated spin-orbit coupling DFT band structures. Our testing includes k-points outside the grid used in the Wannierization, providing an out-of-sample test of accuracy. We illustrate the use of WTBHs with a few example applications. We also develop a web-app that can be used to predict electronic properties on-the-fly using WTBH from our database. The tools to generate the Hamiltonian and the database of the WTB parameters are made publicly available through the websites https://github.com/usnistgov/jarvis and https://jarvis.nist.gov/jarviswtb .

Density Prediction Models for Energetic Compounds Merely Using Molecular Topology

Newly developed high-throughput methods for property predictions make the process of materials design faster and more efficient. Density is an important physical property for energetic compounds to assess detonation velocity and detonation pressure, but the time cost of recent density prediction models is still high owing to the time-consuming processes to calculate molecular descriptors. To improve the screening efficiency of potential energetic compounds, new methods for density prediction with more accuracy and less time cost are urgently needed, and a possible solution is to establish direct mappings between the molecular structure and density. We propose three machine learning (ML) models, support vector machine (SVM), random forest (RF), and Graph neural network (GNN), using molecular topology as the only known input. The widely applied quantitative structure-property relationship based on the density functional theory (DFT-QSPR) is adopted as the benchmark to evaluate the accuracies of the models. All these four models are trained and tested by using the same data set enclosing over 2000 reported nitro compounds searched out from the Cambridge Structural Database. The proportions of compounds with prediction error less than 5% are evaluated by using the independent test set, and the values for the models of SVM, RF, DFT-QSPR, and GNN are 48, 63, 85, and 88%, respectively. The results show that, for the models of SVM and RF, fingerprint bit vectors alone are not facilitated to obtain good QSPRs. Mapping between the molecular structure and density can be well established by using GNN and molecular topology, and its accuracy is slightly better than that of the time-consuming DFT-QSPR method. The GNN-based model has higher accuracy and lower computational resource cost than the widely accepted DFT-QSPR model, so it is more suitable for high-throughput screening of energetic compounds.

Computational scanning tunneling microscope image database

We introduce the systematic database of scanning tunneling microscope (STM) images obtained using density functional theory (DFT) for two-dimensional (2D) materials, calculated using the Tersoff-Hamann method. It currently contains data for 716 exfoliable 2D materials. Examples of the five possible Bravais lattice types for 2D materials and their Fourier-transforms are discussed. All the computational STM images generated in this work are made available on the JARVIS-STM website ( https://jarvis.nist.gov/jarvisstm ). We find excellent qualitative agreement between the computational and experimental STM images for selected materials. As a first example application of this database, we train a convolution neural network model to identify the Bravais lattice from the STM images. We believe the model can aid high-throughput experimental data analysis. These computational STM images can directly aid the identification of phases, analyzing defects and lattice-distortions in experimental STM images, as well as be incorporated in the autonomous experiment workflows.

Density functional theory-based electric field gradient database

The deviation of the electron density around the nuclei from spherical symmetry determines the electric field gradient (EFG), which can be measured by various types of spectroscopy. Nuclear Quadrupole Resonance (NQR) is particularly sensitive to the EFG. The EFGs, and by implication NQR frequencies, vary dramatically across materials. Consequently, searching for NQR spectral lines in previously uninvestigated materials represents a major challenge. Calculated EFGs can significantly aid at the search's inception. To facilitate this task, we have applied high-throughput density functional theory calculations to predict EFGs for 15187 materials in the JARVIS-DFT database. This database, which will include EFG as a standard entry, is continuously increasing. Given the large scope of the database, it is impractical to verify each calculation. However, we assess accuracy by singling out cases for which reliable experimental information is readily available and compare them to the calculations. We further present a statistical analysis of the results. The database and tools associated with our work are made publicly available by JARVIS-DFT ( https://www.ctcms.nist.gov/~knc6/JVASP.html ) and NIST-JARVIS API ( http://jarvis.nist.gov/ ).

Designing and understanding light-harvesting devices with machine learning

Understanding the fundamental processes of light-harvesting is crucial to the development of clean energy materials and devices. Biological organisms have evolved complex metabolic mechanisms to efficiently convert sunlight into chemical energy. Unraveling the secrets of this conversion has inspired the design of clean energy technologies, including solar cells and photocatalytic water splitting. Describing the emergence of macroscopic properties from microscopic processes poses the challenge to bridge length and time scales of several orders of magnitude. Machine learning experiences increased popularity as a tool to bridge the gap between multi-level theoretical models and Edisonian trial-and-error approaches. Machine learning offers opportunities to gain detailed scientific insights into the underlying principles governing light-harvesting phenomena and can accelerate the fabrication of light-harvesting devices.

Multi-directional beam steering using diffractive neural networks

The modern-day resurgence of machine learning has encouraged researchers to revisit older problem spaces from a new perspective. One promising avenue has been implementing deep neural networks to aid in the simulation of physical systems. In the field of optics, densely connected neural networks able to mimic wave propagation have recently been constructed. These diffractive deep neural networks (D²NN) not only offer new insights into wave propagation, but provide a novel tool for investigating and discovering multi-functional diffractive elements. In this paper, we derive an efficient GPU-friendly D²NN methodology based on Rayleigh-Sommerfeld diffraction. We then use the implementation to virtually forge cascades of optical phase masks subject to different beam steering conditions. The input and output conditions we use to train each D²NN instance is based on commercial electro-optic modulated waveguide systems to encourage experimental follow-on. In total, we analyze the beam steering efficacy of 27 individual D²NN instances which explore different permutations of input sources, mask cascades, and output steering targets.

Data-driven discovery of 3D and 2D thermoelectric materials

In this work, we first perform a systematic search for high-efficiency three-dimensional (3D) and two-dimensional (2D) thermoelectric materials by combining semiclassical transport techniques with density functional theory (DFT) calculations and then train machine-learning models on the thermoelectric data. Out of 36 000 three-dimensional and 900 two-dimensional materials currently in the publicly available JARVIS-DFT database, we identify 2932 3D and 148 2D promising thermoelectric materials using a multi-steps screening procedure, where specific thresholds are chosen for key quantities like bandgaps, Seebeck coefficients and power factors. We compute the Seebeck coefficients for all the materials currently in the database and validate our calculations by comparing our results, for a subset of materials, to experimental and existing computational datasets. We also investigate the effect of chemical, structural, crystallographic and dimensionality trends on thermoelectric performance. We predict several classes of efficient 3D and 2D materials such as Ba(MgX)2(X = P, As, Bi), X2YZ6(X = K, Rb, Y=Pd, Pt, Z = Cl, Br), K2PtX2(X = S, Se), NbCu3X4(X = S, Se, Te), Sr2XYO6(X = Ta, Zn, Y=Ga, Mo), TaCu3X4(X = S, Se, Te), and XYN (X = Ti, Zr, Y=Cl, Br). Finally, as high-throughput DFT is computationally expensive, we train machine learning models using gradient boosting decision trees and classical force-field inspired descriptors for n-and p-type Seebeck coefficients and power factors, to quickly pre-screen materials for guiding the next set of DFT calculations. The dataset and tools are made publicly available at the websites:https://www.ctcms.nist.gov/~knc6/JVASP.html,https://www.ctcms.nist.gov/jarvisml/andhttps://jarvis.nist.gov/.

Promising photovoltaic efficiency of a layered silicon oxide crystal Si3O

Computational searching and screening of new functional materials exploiting Earth abundant elements can accelerate the development of their energy applications. Based on the state-of-the-art material search algorithm and ab initio calculations, we demonstrate a recently suggested stable silicon oxide with a layered structure (Si₃O) as an ideal photovoltaic material. With many-body first-principles approaches, the monolayer and layered bulk of Si₃O show direct quasiparticle gaps of 1.85 eV and 1.25 eV, respectively, while an optical gap of about 1.2 eV is nearly independent of the number of layers. Spectroscopic limited maximum efficiency (SLME) is estimated to be 27% for a thickness of 0.5 μm, making it a promising candidate for solar energy applications.

High-Throughput Screening of Antisolvents for the Deposition of High-Quality Perovskite Thin Films

One-step solution deposition of high-quality perovskite thin films relies heavily on a small number of antisolvents. Here, we design a simple minimum volume colorimetric solution assay to screen over 100 different solvents. We correctly identify 14 previously reported antisolvents and predict 20 novel candidates. We then refine the assay through analysis of screening results, available solvent properties, and qualitative evaluation of films cast using 50 candidates. Using the refined findings, we successfully demonstrated 15 different antisolvents for characterization and evaluation in inverted devices, including six previously unreported candidates. All candidates produced power conversion efficiencies comparable to chlorobenzene controls without any additional optimization. This work presents the largest scope of antisolvents reported, can be easily adapted to other perovskites, and opens the door to selecting antisolvents based on a wide range of desirable properties including efficiency, usability, safety, and industrial viability.

High-throughput Discovery of Topologically Non-trivial Materials using Spin-orbit Spillage

We present a novel methodology to identify topologically non-trivial materials based on band inversion induced by spin-orbit coupling (SOC) effect. Specifically, we compare the density functional theory (DFT) based wavefunctions with and without spin-orbit coupling and compute the 'spin-orbit-spillage' as a measure of band-inversion. Due to its ease of calculation, without any need for symmetry analysis or dense k-point interpolation, the spillage is an excellent tool for identifying topologically non-trivial materials. Out of 30000 materials available in the JARVIS-DFT database, we applied this methodology to more than 4835 non-magnetic materials consisting of heavy atoms and low bandgaps. We found 1868 candidate materials with high-spillage (using 0.5 as a threshold). We validated our methodology by carrying out conventional Wannier-interpolation calculations for 289 candidate materials. We demonstrate that in addition to Z2 topological insulators, this screening method successfully identified many semimetals and topological crystalline insulators. Importantly, our approach is applicable to the investigation of disordered or distorted as well as magnetic materials, because it is not based on symmetry considerations. We discuss some individual example materials, as well as trends throughout our dataset, which is available at the websites: https://www.ctcms.nist.gov/~knc6/JVASP.html and https://jarvis.nist.gov/ .