Using scalable computer vision to automate high-throughput semiconductor characterization.

High-throughput materials synthesis methods, crucial for discovering novel functional materials, face a bottleneck in property characterization. These high-throughput synthesis tools produce 104 samples per hour using ink-based deposition while most characterization methods are either slow (conventional rates of 101 samples per hour) or rigid (e.g., designed for standard thin films), resulting in a bottleneck. To address this, we propose automated characterization (autocharacterization) tools that leverage adaptive computer vision for an 85x faster throughput compared to non-automated workflows. Our tools include a generalizable composition mapping tool and two scalable autocharacterization algorithms that: (1) autonomously compute the band gaps of 200 compositions in 6 minutes, and (2) autonomously compute the environmental stability of 200 compositions in 20 minutes, achieving 98.5% and 96.9% accuracy, respectively, when benchmarked against domain expert manual evaluation. These tools, demonstrated on the formamidinium (FA) and methylammonium (MA) mixed-cation perovskite system FA1-xMAxPbI3, 0 ≤ x ≤ 1, significantly accelerate the characterization process, synchronizing it closer to the rate of high-throughput synthesis.

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science.

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable and fundamentally interesting, because they often involve new physical phenomena or new compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) and automated experimentation have been widely proposed to accelerate target identification and synthesis planning. In this Perspective, we argue that the data-driven methods commonly used today are well-suited for optimization but not for the realization of new exceptional materials or molecules. Finding such outliers should be possible using ML, but only by shifting away from using traditional ML approaches that tweak the composition, crystal structure, or reaction pathway. We highlight case studies of high-Tc oxide superconductors and superhard materials to demonstrate the challenges of ML-guided discovery and discuss the limitations of automation for this task. We then provide six recommendations for the development of ML methods capable of exceptional materials discovery: (i) Avoid the tyranny of the middle and focus on extrema; (ii) When data are limited, qualitative predictions that provide direction are more valuable than interpolative accuracy; (iii) Sample what can be made and how to make it and defer optimization; (iv) Create room (and look) for the unexpected while pursuing your goal; (v) Try to fill-in-the-blanks of input and output space; (vi) Do not confuse human understanding with model interpretability. We conclude with a description of how these recommendations can be integrated into automated discovery workflows, which should enable the discovery of exceptional molecules and materials.

Predicting Synthesizability using Machine Learning on Databases of Existing Inorganic Materials.

Defining the metric for synthesizability and predicting new compounds that can be experimentally realized in the realm of data-driven research is a pressing problem in contemporary materials science. The increasing computational power and advancements in machine learning (ML) algorithms provide a new avenue to solve the synthesizability challenge. In this work, using the Inorganic Crystal Structure Database (ICSD) and the Materials Project (MP) database, we represent crystal structures in Fourier-transformed crystal properties (FTCP) representation and use a deep learning model to predict synthesizability in the form of a synthesizability score (SC). Such an SC model, as a synthesizability filter for new materials, enables an efficient and accurate classification to identify promising material candidates. The SC prediction model achieved 82.6/80.6% (precision/recall) overall accuracy in predicting ternary crystal materials. We also trained the SC model by only considering compounds uploaded on the MP before 2015 as the training set and testing on multiple sets of materials uploaded after 2015. In the post-2019 test set, we obtain a high 88.60% true positive rate accuracy, coupled with 9.81% precision, indicating that newly added materials remain unexplored and have high synthesis potential. Further, we provide a list of 100 materials predicted to be synthesizable from this post-2019 dataset (highest SC) for future studies, and our SC model, as a validation filter, is beneficial for future material screening and discovery.

Extracting film thickness and optical constants from spectrophotometric data by evolutionary optimization.

In this paper, we propose a simple and elegant method to extract the thickness and the optical constants of various films from the reflectance and transmittance spectra in the wavelength range of 350 - 1000 nm. The underlying inverse problem is posed here as an optimization problem. To find unique solutions to this problem, we adopt an evolutionary optimization approach that drives a population of candidate solutions towards the global optimum. An ensemble of Tauc-Lorentz Oscillators (TLOs) and an ensemble of Gaussian Oscillators (GOs), are leveraged to compute the reflectance and transmittance spectra for different candidate thickness values and refractive index profiles. This model-based optimization is solved using two efficient evolutionary algorithms (EAs), namely genetic algorithm (GA) and covariance matrix adaptation evolution strategy (CMAES), such that the resulting spectra simultaneously fit all the given data points in the admissible wavelength range. Numerical results validate the effectiveness of the proposed approach in estimating the optical parameters of interest.

Environmental Stability of Crystals: A Greedy Screening.

Discovering materials that are environmentally stable and also exhibit the necessary collection of properties required for a particular application is a perennial challenge in materials science. Herein, we present an algorithm to rapidly screen materials for their thermodynamic stability in a given environment, using a greedy approach. The performance was tested against the standard energy above the hull stability metric for inert conditions. Using data of 126 320 crystals, the greedy algorithm was shown to estimate the driving force for decomposition with a mean absolute error of 39.5 meV/atom, giving it sufficient resolution to identify stable materials. To demonstrate the utility outside of a vacuum, the in-oxygen stability of 39 654 materials was tested. The enthalpy of oxidation was found to be largely exothermic. Further analysis showed that 1438 of these materials fall into the range required for self-passivation based on the Pilling-Bedworth ratio.

A Machine Learning and Computer Vision Approach to Rapidly Optimize Multiscale Droplet Generation.

Generating droplets from a continuous stream of fluid requires precise tuning of a device to find optimized control parameter conditions. It is analytically intractable to compute the necessary control parameter values of a droplet-generating device that produces optimized droplets. Furthermore, as the length scale of the fluid flow changes, the formation physics and optimized conditions that induce flow decomposition into droplets also change. Hence, a single proportional integral derivative controller is too inflexible to optimize devices of different length scales or different control parameters, while classification machine learning techniques take days to train and require millions of droplet images. Therefore, the question is posed, can a single method be created that universally optimizes multiple length-scale droplets using only a few data points and is faster than previous approaches? In this paper, a Bayesian optimization and computer vision feedback loop is designed to quickly and reliably discover the control parameter values that generate optimized droplets within different length-scale devices. This method is demonstrated to converge on optimum parameter values using 60 images in only 2.3 h, 30× faster than previous approaches. Model implementation is demonstrated for two different length-scale devices: a milliscale inkjet device and a microfluidics device.

Predicting Antimicrobial Activity of Conjugated Oligoelectrolyte Molecules via Machine Learning.

New antibiotics are needed to battle growing antibiotic resistance, but the development process from hit, to lead, and ultimately to a useful drug takes decades. Although progress in molecular property prediction using machine-learning methods has opened up new pathways for aiding the antibiotics development process, many existing solutions rely on large data sets and finding structural similarities to existing antibiotics. Challenges remain in modeling unconventional antibiotic classes that are drawing increasing research attention. In response, we developed an antimicrobial activity prediction model for conjugated oligoelectrolyte molecules, a new class of antibiotics that lacks extensive prior structure-activity relationship studies. Our approach enables us to predict the minimum inhibitory concentration for E. coli K12, with 21 molecular descriptors selected by recursive elimination from a set of 5305 descriptors. This predictive model achieves an R2 of 0.65 with no prior knowledge of the underlying mechanism. We find the molecular representation optimum for the domain is the key to good predictions of antimicrobial activity. In the case of conjugated oligoelectrolytes, a representation reflecting the three-dimensional shape of the molecules is most critical. Although it is demonstrated with a specific example of conjugated oligoelectrolytes, our proposed approach for creating the predictive model can be readily adapted to other novel antibiotic candidate domains.

Discovery of temperature-induced stability reversal in perovskites using high-throughput robotic learning.

Stability of perovskite-based photovoltaics remains a topic requiring further attention. Cation engineering influences perovskite stability, with the present-day understanding of the impact of cations based on accelerated ageing tests at higher-than-operating temperatures (e.g. 140°C). By coupling high-throughput experimentation with machine learning, we discover a weak correlation between high/low-temperature stability with a stability-reversal behavior. At high ageing temperatures, increasing organic cation (e.g. methylammonium) or decreasing inorganic cation (e.g. cesium) in multi-cation perovskites has detrimental impact on photo/thermal-stability; but below 100°C, the impact is reversed. The underlying mechanism is revealed by calculating the kinetic activation energy in perovskite decomposition. We further identify that incorporating at least 10 mol.% MA and up to 5 mol.% Cs/Rb to maximize the device stability at device-operating temperature (<100°C). We close by demonstrating the methylammonium-containing perovskite solar cells showing negligible efficiency loss compared to its initial efficiency after 1800 hours of working under illumination at 30°C.

Author Correction: How machine learning can help select capping layers to suppress perovskite degradation.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

How machine learning can help select capping layers to suppress perovskite degradation.

Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI3) films, age them under accelerated conditions, and determine features governing stability using supervised machine learning and Shapley values. We find that organic molecules' low number of hydrogen-bonding donors and small topological polar surface area correlate with increased MAPbI3 film stability. The top performing organic halide, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI3 stability lifetime by 4 ± 2 times over bare MAPbI3 and 1.3 ± 0.3 times over state-of-the-art octylammonium bromide (OABr). Through characterization, we find that this capping layer stabilizes the photoactive layer by changing the surface chemistry and suppressing methylammonium loss.

The Impact of COVID-19-Related Measures on the Solar Resource in Areas with High Levels of Air Pollution.

Restrictions enacted to reduce the spreading of COVID-19 have resulted in notably clearer skies around the world. In this study, we confirm that reduced levels of air pollution correlate with unusually high levels of clear-sky insolation in Delhi, India. Restrictions here were announced on March 19th, with the nation going into lockdown on March 24th. Comparing insolation data before and after these dates with insolation from previous years (2017 to 2019), we observe an 8.3% ± 1.7% higher irradiance than usual in late March and a 5.9% ± 1.6% higher one in April, while we find no significant differences in values from previous years in February or early March. Using results from a previous study, we calculated the expected increase in insolation based on measured PM2.5 concentration levels. Measurements and calculations agree within confidence intervals, suggesting that reduced pollution levels are a major cause for the observed increase in insolation.

Enhanced visible light absorption for lead-free double perovskite Cs2AgSbBr6.

In a search for Pb-free photovoltaic materials, a double perovskite Cs2AgSbBr6 with an indirect optical bandgap of 1.64 eV has been synthesized. Single crystal X-ray diffraction determined the space group as Fm3[combining macron]m with a = 11.1583(7) Å. The black, as-synthesised compound turned brown after heat treatment at 480 K while the symmetry and crystallinity were preserved. X-ray photoelectron spectroscopy indicated the existence of Sb5+ in the black crystals, suggesting that the dark colour arises from the Sb3+-Sb5+ charge transfer. Furthermore, UV visible spectroscopy and density functional theory calculations have been applied to probe the optical properties and electronic structure.

Homogenized halides and alkali cation segregation in alloyed organic-inorganic perovskites.

The role of the alkali metal cations in halide perovskite solar cells is not well understood. Using synchrotron-based nano-x-ray fluorescence and complementary measurements, we found that the halide distribution becomes homogenized upon addition of cesium iodide, either alone or with rubidium iodide, for substoichiometric, stoichiometric, and overstoichiometric preparations, where the lead halide is varied with respect to organic halide precursors. Halide homogenization coincides with long-lived charge carrier decays, spatially homogeneous carrier dynamics (as visualized by ultrafast microscopy), and improved photovoltaic device performance. We found that rubidium and potassium phase-segregate in highly concentrated clusters. Alkali metals are beneficial at low concentrations, where they homogenize the halide distribution, but at higher concentrations, they form recombination-active second-phase clusters.

Promises and challenges of perovskite solar cells.

The efficiencies of perovskite solar cells have gone from single digits to a certified 22.1% in a few years' time. At this stage of their development, the key issues concern how to achieve further improvements in efficiency and long-term stability. We review recent developments in the quest to improve the current state of the art. Because photocurrents are near the theoretical maximum, our focus is on efforts to increase open-circuit voltage by means of improving charge-selective contacts and charge carrier lifetimes in perovskites via processes such as ion tailoring. The challenges associated with long-term perovskite solar cell device stability include the role of testing protocols, ionic movement affecting performance metrics over extended periods of time, and determination of the best ways to counteract degradation mechanisms.

Improving the Carrier Lifetime of Tin Sulfide via Prediction and Mitigation of Harmful Point Defects.

Tin monosulfide (SnS) is an emerging thin-film absorber material for photovoltaics. An outstanding challenge is to improve carrier lifetimes to >1 ns, which should enable >10% device efficiencies. However, reported results to date have only demonstrated lifetimes at or below 100 ps. In this study, we employ defect modeling to identify the sulfur vacancy and defects from Fe, Co, and Mo as most recombination-active. We attempt to minimize these defects in crystalline samples through high-purity, sulfur-rich growth and experimentally improve lifetimes to >3 ns, thus achieving our 1 ns goal. This framework may prove effective for unlocking the lifetime potential in other emerging thin-film materials by rapidly identifying and mitigating lifetime-limiting point defects.

Strongly Enhanced Photovoltaic Performance and Defect Physics of Air-Stable Bismuth Oxyiodide (BiOI).

Bismuth-based compounds have recently gained increasing attention as potentially nontoxic and defect-tolerant solar absorbers. However, many of the new materials recently investigated show limited photovoltaic performance. Herein, one such compound is explored in detail through theory and experiment: bismuth oxyiodide (BiOI). BiOI thin films are grown by chemical vapor transport and found to maintain the same tetragonal phase in ambient air for at least 197 d. The computations suggest BiOI to be tolerant to antisite and vacancy defects. All-inorganic solar cells (ITO|NiOx |BiOI|ZnO|Al) with negligible hysteresis and up to 80% external quantum efficiency under select monochromatic excitation are demonstrated. The short-circuit current densities and power conversion efficiencies under AM 1.5G illumination are nearly double those of previously reported BiOI solar cells, as well as other bismuth halide and chalcohalide photovoltaics recently explored by many groups. Through a detailed loss analysis using optical characterization, photoemission spectroscopy, and device modeling, direction for future improvements in efficiency is provided. This work demonstrates that BiOI, previously considered to be a poor photocatalyst, is promising for photovoltaics.

High Tolerance to Iron Contamination in Lead Halide Perovskite Solar Cells.

The relationship between charge-carrier lifetime and the tolerance of lead halide perovskite (LHP) solar cells to intrinsic point defects has drawn much attention by helping to explain rapid improvements in device efficiencies. However, little is known about how charge-carrier lifetime and solar cell performance in LHPs are affected by extrinsic defects (i.e., impurities), including those that are common in manufacturing environments and known to introduce deep levels in other semiconductors. Here, we evaluate the tolerance of LHP solar cells to iron introduced via intentional contamination of the feedstock and examine the root causes of the resulting efficiency losses. We find that comparable efficiency losses occur in LHPs at feedstock iron concentrations approximately 100 times higher than those in p-type silicon devices. Photoluminescence measurements correlate iron concentration with nonradiative recombination, which we attribute to the presence of deep-level iron interstitials, as calculated from first-principles, as well as iron-rich particles detected by synchrotron-based X-ray fluorescence microscopy. At moderate contamination levels, we witness prominent recovery of device efficiencies to near-baseline values after biasing at 1.4 V for 60 s in the dark. We theorize that this temporary effect arises from improved charge-carrier collection enhanced by electric fields strengthened from ion migration toward interfaces. Our results demonstrate that extrinsic defect tolerance contributes to high efficiencies in LHP solar cells, which inspires further investigation into potential large-scale manufacturing cost savings as well as the degree of overlap between intrinsic and extrinsic defect tolerance in LHPs and "perovskite-inspired" lead-free stable alternatives.

Highly tensile-strained Ge/InAlAs nanocomposites.

Self-assembled nanocomposites have been extensively investigated due to the novel properties that can emerge when multiple material phases are combined. Growth of epitaxial nanocomposites using lattice-mismatched constituents also enables strain-engineering, which can be used to further enhance material properties. Here, we report self-assembled growth of highly tensile-strained Ge/In0.52Al0.48As (InAlAs) nanocomposites by using spontaneous phase separation. Transmission electron microscopy shows a high density of single-crystalline germanium nanostructures coherently embedded in InAlAs without extended defects, and Raman spectroscopy reveals a 3.8% biaxial tensile strain in the germanium nanostructures. We also show that the strain in the germanium nanostructures can be tuned to 5.3% by altering the lattice constant of the matrix material, illustrating the versatility of epitaxial nanocomposites for strain engineering. Photoluminescence and electroluminescence results are then discussed to illustrate the potential for realizing devices based on this nanocomposite material.

A Two-Step Absorber Deposition Approach To Overcome Shunt Losses in Thin-Film Solar Cells: Using Tin Sulfide as a Proof-of-Concept Material System.

As novel absorber materials are developed and screened for their photovoltaic (PV) properties, the challenge remains to reproducibly test promising candidates for high-performing PV devices. Many early-stage devices are prone to device shunting due to pinholes in the absorber layer, producing "false-negative" results. Here, we demonstrate a device engineering solution toward a robust device architecture, using a two-step absorber deposition approach. We use tin sulfide (SnS) as a test absorber material. The SnS bulk is processed at high temperature (400 °C) to stimulate grain growth, followed by a much thinner, low-temperature (200 °C) absorber deposition. At a lower process temperature, the thin absorber overlayer contains significantly smaller, densely packed grains, which are likely to provide a continuous coating and fill pinholes in the underlying absorber bulk. We compare this two-step approach to the more standard approach of using a semi-insulating buffer layer directly on top of the annealed absorber bulk, and we demonstrate a more than 3.5× superior shunt resistance Rsh with smaller standard error σRsh. Electron-beam-induced current (EBIC) measurements indicate a lower density of pinholes in the SnS absorber bulk when using the two-step absorber deposition approach. We correlate those findings to improvements in the device performance and device performance reproducibility.