The practically unlimited high-dimensional composition space of high-entropy materials (HEMs) has emerged as an exciting platform for functional materials design and discovery. However, the identification of stable and synthesizable HEMs and robust design rules remains a daunting challenge due to the difficulty in determining composition/structure-specific enthalpy and entropy contributions to the stability and formation of HEMs. In this work, using first-principles calculations, we find that (i) the stability and miscibility of HEMs strongly depend on the formation enthalpy of the HEM relative to the most stable completing phase rather than on the conventionally-viewed enthalpies of mixing over all possible competing phases, and (ii) the entropy forming ability of a HEM can be measured from the defect formation energy spectrum of tens of substitutional defects in ordered binary compounds, involving no sampling over numerous alloy configurations. Based on these findings, we propose a highly predictive Mixed Enthalpy-Entropy Descriptor (MEED), which enables the rational high-throughput first-principles design and screening of new HEMs over large chemical spaces. Applying the MEED to two structurally distinct material systems (i.e., 3D rocksalt carbides and 2D layered sulfides), not only all experimentally reported HEMs within each system are successfully identified, but a universal cutoff criterion for assessing their relative synthesizability also revealed. In addition, tens of new high entropy carbides and 2D high-entropy sulfides are also predicted. They have the potential for a wide variety of applications such as coating in aerospace devices, energy conversion and storage, and flexible electronics.
Lowering the Exponential Wall: Accelerating High-Entropy Alloy Catalysts Screening using Local Surface Energy Descriptors from Neural Network Potentials
Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations are the computational tool of choice to obtain energies of crystals with quantitative accuracy. Despite algorithmic and computing advances, DFT calculations remain comparatively expensive and scale poorly with system size. Here we show that deep neural networks utilizing just two descriptors - the Pauling electronegativity and ionic radii - can predict the DFT formation energies of C3A2D3O12 garnets with extremely low mean absolute errors of 7-8 meV/atom…
We employ a descriptor based machine-learning approach to assess the effect of chemical alloying on formation-enthalpy of rare-earth intermetallics. Application of machine-learning approaches in rare-earth intermetallic design have been sparse due to limited availability of reliable datasets. In this work, we developed an `in-house' rare-earth database with more than 600$+$ compounds, each entry was populated with formation enthalpy and related atomic features using high-throughput density-functional theory (DFT). The SISSO (sure independence screening and sparsifying operator) based machine-l…
Reliable, clean transfer and interfacing of 2D material layers is technologically as important as their growth. Bringing both together remains a challenge due to the vast, interconnected parameter space. We introduce a fast-screening descriptor approach to demonstrate holistic data-driven optimization across the entirety of process steps for the graphene-Cu model system. We map the crystallographic dependencies of graphene chemical vapor deposition, interfacial Cu oxidation to decouple graphene, and its dry delamination across inverse pole figures. Their overlay enables us to identify hitherto…
Materials Expert-Artificial Intelligence for Materials Discovery
Department of Physics, Cornell University, Ithaca, NY 14853, USA；Department of Chemistry, Princeton University, Princeton, New Jersey 08544, United States；Department of Chemistry, North Carolina State University, Raleigh, NC, USA；New York University, New York, NY 10011, USA；Fraunhofer Research Institution for Materials Recycling；Department of Physics, Ewha Womans University, Seoul, South Korea
The large-scale search for high-performing candidate 2D materials is limited to calculating a few simple descriptors, usually with first-principles density functional theory calculations. In this work, we alleviate this issue by extending and generalizing crystal graph convolutional neural networks to systems with planar periodicity, and train an ensemble of models to predict thermodynamic, mechanical, and electronic properties. To demonstrate the utility of this approach, we carry out a screening of nearly 45,000 structures for two largely disjoint applications: namely, mechanically robust co…
Artificial Intelligence-Enabled Holistic Design of Catalysts Tailored for Semiconducting Carbon Nanotube Growth
Peking University（北京大学）；National Center for Nanoscience and Technology（国家纳米科学中心）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；Suzhou Laboratory（苏州实验室）
Backward Mapping from Device Targets to Chemical Genomes for Interpretable Discovery of Phase-Stable Lead-Free Double Perovskites with DFT-Validated Design Rules
RAI Initiative Ltd（RAI倡议有限公司）；Bangladesh University of Textiles（孟加拉国纺织大学）；Universiti Putra Malaysia（马来西亚博特拉大学）；Institute of Science Tokyo（东京科学研究所）；University of Liege（列日大学）
Harnessing the recent advance in data science and materials science, it is feasible today to build predictive models for materials properties. In this study, we employ the data of high-throughput quantum mechanics calculations based on 170,714 inorganic crystalline compounds to train a machine learning model for formation energy prediction. Different from the previous work, our model reaches a fairly good predictive ability (R2=0.982 and MAE=0.07 eVatom-1, DenseNet model) and meanwhile can be universally applied to the large phase space of inorganic materials. The improvement comes from severa…
Thermoelectric (TE) materials are among very few sustainable yet feasible energy solutions of present time. This huge promise of energy harvesting is contingent on identifying/designing materials having higher efficiency than presently available ones. However, due to the vastness of the chemical space of materials, only its small fraction was scanned experimentally and/or computationally so far. Employing a compressed-sensing based symbolic regression in an active-learning framework, we have not only identified a trend in materials' compositions for superior TE performance, but have also predi…
EGMOF: Efficient Generation of Metal-Organic Frameworks Using a Hybrid Diffusion-Transformer Architecture
Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology（韩国科学技术院化学与生物分子工程系）；Department of Chemistry, University of Toronto（多伦多大学化学系）；Vector Institute for Artificial Intelligence（人工智能矢量研究所）；Department of Chemistry, Sungkyunkwan University（成均馆大学化学系）；Acceleration Consortium（加速联盟）；Department of Computer Science, University of Toronto（多伦多大学计算机科学系）；Department of Materials Science & Engineering, University of Toronto（多伦多大学材料科学与工程系）；Department of Chemical Engineering & Applied Chemistry, University of Toronto（多伦多大学化学工程与应用化学系）；Canadian Institute for Advanced Research (CIFAR)（加拿大高级研究 institute (CIFAR)）；NVIDIA
Developing fast and accurate methods to discover intermetallic compounds is relevant for alloy design. While density-functional-theory (DFT)-based methods have accelerated design of binary and ternary alloys by providing rapid access to the energy and properties of the stable intermetallics, they are not amenable for rapidly screening the vast combinatorial space of multi-principal element alloys (MPEAs). Here, a machine-learning model is presented for predicting the formation enthalpy of binary intermetallics and used to identify new ones. The model uses easily accessible elemental properties…
Genome-Guided Interpretable Screening of Phase-Stable, Lead-Free Double Perovskite Absorbers for All-Inorganic Semiconductors, Sensors, and Photovoltaics with DFT-Validated Design Rules
Research and Analysis Institute, RAI Initiative Ltd（拉伊倡议有限公司研究与分析研究所）；Bangladesh University of Textiles（孟加拉国纺织大学）；Universiti Putra Malaysia（马来西亚博特拉大学）；Institute of Science Tokyo（东京科学大学）；University of Évora（埃武拉大学）；Daffodil International University（达富迪尔国际大学）；University of Idaho（爱达荷大学）；North Carolina A&T State University（北卡罗来纳州立农业技术大学）
Symmetry-Aware Bayesian Flow Networks for Crystal Generation
Institute of Theoretical Informatics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院理论信息学研究所）；Institute of Nanotechnology, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院纳米技术研究所）
