Rapidly discovering functional materials remains an open challenge because the traditional trial-and-error methods are usually inefficient especially when thousands of candidates are treated. Here, we develop a target-driven method to predict undiscovered hybrid organic-inorganic perovskites (HOIPs) for photovoltaics. This strategy, combining machine learning techniques and density functional theory calculations, aims to quickly screen the HOIPs based on bandgap and solve the problems of toxicity and poor environmental stability in HOIPs. Successfully, six orthorhombic lead-free HOIPs with proper bandgap for solar cells and room temperature thermal stability are screened out from 5158 unexplored HOIPs and two of them stand out with direct bandgaps in the visible region and excellent environmental stability. Essentially, a close structure-property relationship mapping the HOIPs bandgap is established. Our method can achieve high accuracy in a flash and be applicable to a broad class of functional material design.
2D ferromagnetic (FM) semiconductors/half‐metals/metals are the key materials toward next‐generation spintronic devices. However, such materials are still rather rare and the material search space is too large to explore exhaustively. Here, an adaptive framework to accelerate the discovery of 2D intrinsic FM materials is developed, by combining advanced machine‐learning (ML) techniques with high‐throughput density functional theory calculations. Successfully, about 90 intrinsic FM materials with desirable bandgap and excellent thermodynamic stability are screened out and a database containing 1459 2D magnetic materials is set up. To improve the performance of ML models on small‐scale datasets like diverse 2D materials, a crystal graph multilayer descriptor using the elemental property is proposed, with which ML models achieve prediction accuracy over 90% on thermodynamic stability, magnetism, and bandgap. This study not only provides dozens of compelling FM candidates for future spintronics, but also paves a feasible route for ML‐based rapid screening of diverse structures and/or complex properties.
Theoretical methods and models for the description of thermodynamics and kinetics in electro-catalysis, including solvent effects, externally applied potentials, and many-body interactions, are discussed.
Rapid discovery of novel functional materials is urgent but a tremendous challenge using trial‐and‐error methods in vast chemical space. Here, a multistep screening scheme is developed by combining high‐throughput calculations and machine learning (ML) techniques. Successfully, 151 promising stable ferroelectric photovoltaic (FPV) perovskites with proper bandgap are screened out from 19 841 candidate compositions. Two new descriptors are proposed to describe mixed inorganic perovskites' formability through ML feature engineering. Additionally, phase‐transition energy difference is used as a criterion for directly judging whether the compound can expose spontaneous polarization. The ML prediction accuracy of both energy difference and bandgap regressions is over 90% and ML produces comparable results to density functional theory calculations. Moreover, bandgaps of eight selected FPV perovskites are all close to the optimal value of single‐junction solar cells. This scheme not only realizes the ML acceleration for targeted multiproperty materials' design and expansion of materials database, but also opens a way for descriptor development.
Salinity and high temperature are major abiotic stresses limiting sustainable crop production. Seed priming is a useful tool to enhance seedling growth and the antioxidant defence system of crops under salinity and temperature stress. This experiment was designed to determine the effects of gibberellic acid (GA3, 288.7 µm), kinetin (232.2 µm) and salicylic acid (362 µm) on some morphological and physiological parameters of sweet sorghum (Sorghum bicolor L. Moench) hybrid Yajin 13 under salinity (0, 100 and 200 mm NaCl) and temperature (25°C and 37°C) stress. Salinity and high temperature significantly reduced emergence percentage, shoot and root lengths, number of leaves, shoot fresh and dry weight, and chlorophyll a and b content. The activity of superoxide dismutase (SOD) and malondialdehyde (MDA) content were increased with an increase in both salinity and temperature stress. Hormone treatments positively affected all parameters except root fresh and dry weight, number of leaves, SOD activity and chlorophyll a. Under salinity stress at 200 mm NaCl, treatment with salicylic acid increased emergence percentage, emergence rate, chlorophyll b and protein content by 82.0%, 130%, 7.9% and 1.9%, respectively, relative to the control (no treatment). At 37°C, salicylic acid increased emergence percentage, emergence rate and number of roots by 72.5%, 108.5% and 63.8%, respectively, and decreased MDA content by 17.6% relative to the control. Our study indicated that seed priming with an appropriate concentration of exogenous hormones (salicylic acid, kinetin, GA3) is a useful, easy method for improving germination, seedling growth and the antioxidant defence system of sweet sorghum under conditions of high temperature and salinity.
Property-oriented material design is a persistent pursuit for material scientists. Recently, machine learning (ML) as a powerful new tool has attracted worldwide attention in the material design field. Based on statistics instead of solving physical equations, ML can predict material properties faster with lower cost. Because of its data-driven characteristics, the quantity and quality of material data become the keys to the practical applications of this technique. In this Perspective, problems caused by lack of data and diversity of data are discussed. Various approaches, including high-throughput calculations, database construction, feedback loop algorithms, and better descriptors, have been exploited to address these problems. It is expected that this Perspective will bring data itself to the forefront of MLbased material design.
Supported catalysts have exhibited excellent performance in various reactions. However, the rational design of supported catalysts with high activity and certain selectivity remains a great challenge because of the complicated interfacial effects. Using recently emerged two-dimensional materials supported dual-atom catalysts (DACs@2D) as a prototype, we propose a simple and universal descriptor based on inherent atomic properties (electronegativity, electron type, and number), which can well evaluate the complicated interfacial effects on the electrochemical reduction reactions (i.e., CO 2 , O 2 , and N 2 reduction reactions). Based on this descriptor, activity and selectivity trends in CO 2 reduction reaction are successfully elucidated, in good agreement with available experimental data. Moreover, several potential catalysts with superior activity and selectivity for target products are predicted, such as CuCr/g-C 3 N 4 for CH 4 and CuSn/N-BN for HCOOH. More importantly, this descriptor can also be extended to evaluate the activity of DACs@2D for O 2 and N 2 reduction reactions, with very small errors between the prediction and reported experimental/computational results. This work provides feasible principles for the rational design of advanced electrocatalysts and the construction of universal descriptors based on inherent atomic properties.
Developing high‐performance catalysts using traditional trial‐and‐error methods is generally time consuming and inefficient. Here, by combining machine learning techniques and first‐principle calculations, we are able to discover novel graphene‐supported single‐atom catalysts for nitrogen reduction reaction in a rapid way. Successfully, 45 promising catalysts with highly efficient catalytic performance are screened out from 1626 candidates. Furthermore, based on the optimal feature sets, new catalytic descriptors are constructed via symbolic regression, which can be directly used to predict single‐atom catalysts with good accuracy and good generalizability. This study not only provides dozens of promising catalysts and new descriptors for nitrogen reduction reaction but also offers a potential way for rapid screening of new electrocatalysts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.