Abstract
X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine learning-enabled ...approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal-halides spanning three dimensionalities and seven space groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross-validated accuracies for dimensionality and space group classification of 93 and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16° 2
θ
, which enables an XRD pattern to be obtained and classified in 5.5 min or less.
Abstract
Bayesian optimization (BO) has been leveraged for guiding autonomous and high-throughput experiments in materials science. However, few have evaluated the efficiency of BO across a broad ...range of experimental materials domains. In this work, we quantify the performance of BO with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems. By defining acceleration and enhancement metrics for materials optimization objectives, we find that surrogate models such as Gaussian Process (GP) with anisotropic kernels and Random Forest (RF) have comparable performance in BO, and both outperform the commonly used GP with isotropic kernels. GP with anisotropic kernels has demonstrated the most robustness, yet RF is a close alternative and warrants more consideration because it is free from distribution assumptions, has smaller time complexity, and requires less effort in initial hyperparameter selection. We also raise awareness about the benefits of using GP with anisotropic kernels in future materials optimization campaigns.
Abstract
In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a ...machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.
Si based tandem solar cells represent an alternative to traditional compound III-V multijunction cells as a promising way to achieve high efficiencies. A theoretical study on the energy yield of GaAs ...on Si (GaAs/Si) tandem solar cells is performed to assess their energy yield potential under realistic illumination conditions with varying spectrum. We find that the yield of a 4-terminal contact scheme with thick top cell is more than 15% higher than for a 2-terminal scheme. Furthermore, we quantify the main losses that occur for this type of solar cell under varying spectra. Apart from current mismatch, we find that a significant power loss can be attributed to low irradiance seen by the sub-cells. The study shows that despite non-optimal bandgap combination, GaAs/Si tandem solar cells have the potential to surpass 30% energy conversion efficiency.
Combining high‐throughput experiments with machine learning accelerates materials and process optimization toward user‐specified target properties. In this study, a rapid machine learning‐driven ...automated flow mixing setup with a high‐throughput drop‐casting system is introduced for thin film preparation, followed by fast characterization of proxy optical and target electrical properties that completes one cycle of learning with 160 unique samples in a single day, a >10× improvement relative to quantified, manual‐controlled baseline. Regio‐regular poly‐3‐hexylthiophene is combined with various types of carbon nanotubes, to identify the optimum composition and synthesis conditions to realize electrical conductivities as high as state‐of‐the‐art 1000 S cm−1. The results are subsequently verified and explained using offline high‐fidelity experiments. Graph‐based model selection strategies with classical regression that optimize among multi‐fidelity noisy input‐output measurements are introduced. These strategies present a robust machine‐learning driven high‐throughput experimental scheme that can be effectively applied to understand, optimize, and design new materials and composites.
A graph‐based regressor and optimizer for high‐throughput multi‐fidelity, noisy experiments that designs electronically conducting composites is presented. An automated flow mixing and drop‐casting setup for P3HT‐CNT thin film preparation, followed by rapid characterization of optical and electrical properties of 160 unique samples per day, a >10× improvement relative to baseline, realizing electrical conductivities as high as ≈1000 S cm−1 is presented.
Abstract
Needle-in-a-Haystack problems exist across a wide range of applications including rare disease prediction, ecological resource management, fraud detection, and material property ...optimization. A Needle-in-a-Haystack problem arises when there is an extreme imbalance of optimum conditions relative to the size of the dataset. However, current state-of-the-art optimization algorithms are not designed with the capabilities to find solutions to these challenging multidimensional Needle-in-a-Haystack problems, resulting in slow convergence or pigeonholing into a local minimum. In this paper, we present a Zooming Memory-Based Initialization algorithm, entitled ZoMBI, that builds on conventional Bayesian optimization principles to quickly and efficiently optimize Needle-in-a-Haystack problems in both less time and fewer experiments. The ZoMBI algorithm demonstrates compute time speed-ups of 400× compared to traditional Bayesian optimization as well as efficiently discovering optima in under 100 experiments that are up to 3× more highly optimized than those discovered by similar methods.
Non-concentrating tandem solar cells offer the potential to increase conversion efficiencies beyond 30%. Of particular interest are configurations with a silicon bottom cell – to leverage existing ...manufacturing infrastructure – and III-V compound semiconductor top cells to combine high efficiencies with long-term stability and experience in applications. In this work we investigate the GaAs/GaAs/Si triple-junction architecture. GaAs and Si form a non-ideal bandgap combination, which poses a challenge to the current matching requirement. As band-to-band absorption in GaAs is almost two thirds of that in Si, absorption can be balanced by replacing the GaAs top junction with a GaAs/GaAs double junction. This opens up a possibility for an integrated two terminal solar cell for the GaAs-Si material system. In this study, we numerically evaluate the efficiency and energy yield potential of the GaAs/GaAs/Si triple-junction architecture. We find that, with state-of-the-art material quality, the GaAs/GaAs/Si architecture has the potential to achieve 33.0% efficiency, and harvesting efficiencies between 31.4% and 32.1%. We fabricated a GaAs/GaAs/Si four-terminal tandem solar cell with a mathematically combined efficiency of 20.4%.
In electrolytic capacitorless permanent magnet synchronous motor (PMSM) drives, the DC-link voltage will fluctuate in a wide range due to the use of slim film capacitor. When the flux-weakening ...current is lower than −ψf/Ld during the high speed operation, the flux-weakening control loop will transform to a positive feedback mode, which means the reduction of flux-weakening current will lead to the acceleration of the voltage saturation, thus the whole system will be unstable. In order to solve this issue, this paper proposes a novel flux-weakening method for electrolytic capacitorless motor drives to maintain a negative feedback characteristic of the control loop during high speed operation. Based on the analysis of the instability mechanism in flux-weakening region, a quadrature voltage constrain mechanism is constructed to stabilize the system. Meanwhile, the parameters of the controller are theoretically designed for easier industrial application. The proposed algorithm is implemented on a 1.5kW electrolytic capacitorless PMSM drive to verify the effectiveness of the flux-weakening performance.
Process optimization of photovoltaic devices is a time-intensive, trial-and-error endeavor, which lacks full transparency of the underlying physics and relies on user-imposed constraints that may or ...may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach for gallium arsenide (GaAs) solar cells that identifies the root cause(s) of underperformance with layer-by-layer resolution and reveals alternative optimal process windows beyond traditional black-box optimization. Our Bayesian network approach links a key GaAs process variable (growth temperature) to material descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency). For this purpose, we combine a Bayesian inference framework with a neural network surrogate device-physics model that is 100× faster than numerical solvers. With the trained surrogate model and only a small number of experimental samples, our approach reduces significantly the time-consuming intervention and characterization required by the experimentalist. As a demonstration of our method, in only five metal organic chemical vapor depositions, we identify a superior growth temperature profile for the window, bulk, and back surface field layer of a GaAs solar cell, without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above traditional grid search methods.
We demonstrate a numerical analysis of the device impact of photon reabsorption on single-junction GaAs and tandem GaAs/Si solar cells. A self-consistent optical-electrical model that considers ...nonideal losses within the devices is developed. For single-junction devices, we find that the impact of photon recycling on the voltage increases monotonically with the injection level. For record-level GaAs solar cells, the voltage boost is 33 mV under open-circuit conditions and 13 mV at the maximum power point. For tandem GaAs/Si solar cells, photon reabsorption moderates the sensitivity of tandem efficiency to both obvious parameters like absorber thickness and implicit parameters like shunt resistance (R sh ) and bulk lifetime. Considering luminescent coupling results in a GaAs top cell that is 9.5% thicker than without luminescent coupling. The tandem device is 50% more sensitive to R sh changes in the GaAs cell than R sh changes in the Si cell. The impact of the GaAs top-cell bulk lifetime on tandem efficiency is reduced by 61% if photon reabsorption is not considered. This integrated optoelectronic device model allows one quantification of the implicit effects of photon recycling and luminescent coupling on device parameters for GaAs/Si tandem, providing a valuable tool for high-performance device optimization.