As the materials science community seeks to capitalize on recent advancements in computer science, the sparsity of well-labelled experimental data and limited throughput by which it can be generated ...have inhibited deployment of machine learning algorithms to date. Several successful examples in computational chemistry have inspired further adoption of machine learning algorithms, and in the present work we present autoencoding algorithms for measured optical properties of metal oxides, which can serve as an exemplar for the breadth and depth of data required for modern algorithms to learn the underlying structure of experimental materials science data. Our set of 178 994 distinct materials samples spans 78 distinct composition spaces, includes 45 elements, and contains more than 80 000 unique quinary oxide and 67 000 unique quaternary oxide compositions, making it the largest and most diverse experimental materials set utilized in machine learning studies. The extensive dataset enabled training and validation of 3 distinct models for mapping between sample images and absorption spectra, including a conditional variational autoencoder that generates images of hypothetical materials with tailored absorption properties. The absorption patterns auto-generated from sample images capture the salient features of ground truth spectra, and band gap energies extracted from these auto-generated patterns are quite accurate with a mean absolute error of 180 meV, which is the approximate uncertainty from traditional extraction of the band gap energy from measurements of the full transmission and reflection spectra. Optical properties of materials are not only ubiquitous in materials applications but also emblematic of the confluence of underlying physical phenomena yielding the type of complex data relationships that merit and benefit from neural network-type modelling.
Sequential learning (SL) strategies,
i.e.
iteratively updating a machine learning model to guide experiments, have been proposed to significantly accelerate materials discovery and research. ...Applications on computational datasets and a handful of optimization experiments have demonstrated the promise of SL, motivating a quantitative evaluation of its ability to accelerate materials discovery, specifically in the case of physical experiments. The benchmarking effort in the present work quantifies the performance of SL algorithms with respect to a breadth of research goals: discovery of any "good" material, discovery of all "good" materials, and discovery of a model that accurately predicts the performance of new materials. To benchmark the effectiveness of different machine learning models against these goals, we use datasets in which the performance of all materials in the search space is known from high-throughput synthesis and electrochemistry experiments. Each dataset contains all pseudo-quaternary metal oxide combinations from a set of six elements (chemical space), the performance metric chosen is the electrocatalytic activity (overpotential) for the oxygen evolution reaction (OER). A diverse set of SL schemes is tested on four chemical spaces, each containing 2121 catalysts. The presented work suggests that research can be accelerated by up to a factor of 20 compared to random acquisition in specific scenarios. The results also show that certain choices of SL models are ill-suited for a given research goal resulting in substantial deceleration compared to random acquisition methods. The results provide quantitative guidance on how to tune an SL strategy for a given research goal and demonstrate the need for a new generation of materials-aware SL algorithms to further accelerate materials discovery.
Benchmarking metrics for materials discovery
via
sequential learning are presented, to assess the efficacy of existing algorithms and to be scientific in our assessment of accelerated science.
Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. ...Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec's ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.
Solar photoelectrochemical generation of fuel is a promising energy technology yet the lack of an efficient, robust photoanode remains a primary materials challenge in the development and deployment ...of solar fuels generators. Metal oxides comprise the most promising class of photoanode materials, but no known material meets the demanding requirements of low band gap energy, photoelectrocatalysis of the oxygen evolution reaction (OER), and stability under highly oxidizing conditions. Here, the identification of new photoelectroactive materials is reported through a strategic combination of combinatorial materials synthesis, high‐throughput photoelectrochemistry, optical spectroscopy, and detailed electronic structure calculations. Four photoelectrocatalyst phases, α‐Cu2V2O7, β‐Cu2V2O7,γ‐Cu3V2O8, and Cu11V6O26, are reported with band gap energy at or below 2 eV. The photoelectrochemical properties and 30 min stability of these copper vanadate phases are demonstrated in three different aqueous electrolytes (pH 7, pH 9, and pH 13), with select combinations of phase and electrolyte exhibiting unprecedented photoelectrocatalytic stability for metal oxides with sub‐2 eV band gap. Through integration of experimental and theoretical techniques, new structure‐property relationships are determined and establish CuO–V2O5 as the most prominent composition system for OER photoelectrocatalysts, providing crucial information for materials genomes initiatives and paving the way for continued development of solar fuels photoanodes.
Through integration of high throughput experimental and theoretical techniques, CuO‐V2O5 is established as the most prominent composition system for oxygen evolution reaction photoelectrocatalysts. Four photoelectrocatalyst phases are discovered and structure–property relationships are developed using a strategic combination of combinatorial synthesis, high throughput screening, and detailed electronic structure calculations.
Combinatorial synthesis and screening for discovery of electrocatalysts has received increasing attention, particularly for energy-related technologies. High-throughput discovery strategies typically ...employ a fast, reliable initial screening technique that is able to identify active catalyst composition regions. Traditional electrochemical characterization via current–voltage measurements is inherently throughput-limited, as such measurements are most readily performed by serial screening. Parallel screening methods can yield much higher throughput and generally require the use of an indirect measurement of catalytic activity. In a water-splitting reaction, the change of local pH or the presence of oxygen and hydrogen in the solution can be utilized for parallel screening of active electrocatalysts. Previously reported techniques for measuring these signals typically function in a narrow pH range and are not suitable for both strong acidic and basic environments. A simple approach to screen the electrocatalytic activities by imaging the oxygen and hydrogen bubbles produced by the oxygen evolution reaction (OER) and hydrogen evolution reaction (HER) is reported here. A custom built electrochemical cell was employed to record the bubble evolution during the screening, where the testing materials were subject to desired electrochemical potentials. The transient of the bubble intensity obtained from the screening was quantitatively analyzed to yield a bubble figure of merit (FOM) that represents the reaction rate. Active catalysts in a pseudoternary material library, (Ni–Fe–Co)O x , which contains 231 unique compositions, were identified in less than one minute using the bubble screening method. An independent, serial screening method on the same material library exhibited excellent agreement with the parallel bubble screening. This general approach is highly parallel and is independent of solution pH.
Abstract
Machine learning for materials science envisions the acceleration of basic science research through automated identification of key data relationships to augment human interpretation and ...gain scientific understanding. A primary role of scientists is extraction of fundamental knowledge from data, and we demonstrate that this extraction can be accelerated using neural networks via analysis of the trained data model itself rather than its application as a prediction tool. Convolutional neural networks excel at modeling complex data relationships in multi-dimensional parameter spaces, such as that mapped by a combinatorial materials science experiment. Measuring a performance metric in a given materials space provides direct information about (locally) optimal materials but not the underlying materials science that gives rise to the variation in performance. By building a model that predicts performance (in this case photoelectrochemical power generation of a solar fuels photoanode) from materials parameters (in this case composition and Raman signal), subsequent analysis of gradients in the trained model reveals key data relationships that are not readily identified by human inspection or traditional statistical analyses. Human interpretation of these key relationships produces the desired fundamental understanding, demonstrating a framework in which machine learning accelerates data interpretation by leveraging the expertize of the human scientist. We also demonstrate the use of neural network gradient analysis to automate prediction of the directions in parameter space, such as the addition of specific alloying elements, that may increase performance by moving beyond the confines of existing data.
The Materials Provenance Store Statt, Michael J; Rohr, Brian A; Guevarra, Dan ...
Scientific data,
04/2023, Letnik:
10, Številka:
1
Journal Article
Recenzirano
Odprti dostop
We present a database resulting from high throughput experimentation, primarily on metal oxide solid state materials. The central relational database, the Materials Provenance Store (MPS), manages ...the metadata and experimental provenance from acquisition of raw materials, through synthesis, to a broad range of materials characterization techniques. Given the primary research goal of materials discovery of solar fuels materials, many of the characterization experiments involve electrochemistry, along with optical, structural, and compositional characterizations. The MPS is populated with all information required for executing common data queries, which typically do not involve direct query of raw data. The result is a database file that can be distributed to users so that they can independently execute queries and subsequently download the data of interest. We propose this strategy as an approach to manage the highly heterogeneous and distributed data that arises from materials science experiments, as demonstrated by the management of over 30 million experiments run on over 12 million samples in the present MPS release.
Optical absorption spectroscopy is an important materials characterization for applications such as solar energy generation. This data descriptor describes the to date (Dec 2018) largest publicly ...available curated materials science dataset for near infrared to near UV (UV-Vis) light absorbance, composition and processing properties of metal oxides. By supplying the complete synthesis and processing history of each of the 179072 samples from 99965 unique compositions we believe the dataset will enable the community to develop predictive models for materials, such as prediction of optical properties based on composition and processing, and ultimately serve as a benchmark dataset for continued integration of machine learning in materials science. The dataset is also a resource for identifying materials composition and synthesis to attain specific optical properties.
The importance of metal oxide photoanodes in solar fuels technology has garnered concerted efforts in photoanode discovery in recent decades, which complement parallel efforts in development of ...analytical techniques and optimization strategies using standard photoanodes such as TiO2, Fe2O3 and BiVO4. Theoretical guidance of high-throughput experiments has been particularly effective in dramatically increasing the portfolio of metal oxide photoanodes, motivating a new era of photoanode development where the characterization and optimization techniques developed on traditional materials are applied to nascent photoanodes that exhibit visible light photoresponse. The compendium of metal oxide photoanodes presented in the present work can also serve as the basis for further technique development, with a primary goal to establish workflows for discovery of materials that perform better against the critical criteria of operational stability, visible light photoresponse, and photovoltage suitable for tandem absorber architectures.
PDF
