An Ensemble Learning Platform for the Large-Scale Exploration of New Double Perovskites

Interpretable Surrogate Learning for Electronic Material Generation

Despite many accessible AI models that have been developed, it is an open challenge to fully exploit interpretable insights to enable effective materials design and develop materials with desired properties for target applications. Here, we introduce an interpretable surrogate learning framework that can actively design and generate electronic materials (EMGen), akin to producing updated materials with requirements by screening all possible elements and fractions. Taking the materials system with required band gaps as a case study, EMGen exhibits a benchmarking predictive error and a running time of 1.7 min for designing and producing a structure with a desired band gap. Using EMGen, we establish a large hybrid functional band gap database, and more uplifting is that the proposed EMGen effectively designs GaxOy with a wide band gap (>5.0 eV) for deep ultraviolet (DUV) optoelectronic devices, enabling a breakthrough extension of the applicability of GaxOy films in photodetectors to DUV light below 240 nm. The augmented band gap also helps improve the breakdown voltage and the heat resilience performance of the amorphous GaxOy film, thereby achieving considerable potential within the realm of power electronics applications. The proposed EMGen, as a specialized, interpretable AI model for the generation of electronic materials, is demonstrated to be an essential tool for on-demand semiconductor materials design.

Enhancing Superconductor Critical Temperature Prediction: A Novel Machine Learning Approach Integrating Dopant Recognition

Doping plays a crucial role in determining the critical temperature (Tc) of superconductors, yet accurately predicting its effects remains a significant challenge. Here, we introduce a novel doping descriptor that captures the complex influence of dopants on superconductivity. By integrating the doping descriptor with elemental and physical features within a Mixture of Experts (MoE) model, we achieve a remarkable R2 of 0.962 for Tc prediction, surpassing all published prediction models. Our approach successfully identifies optimal doping levels in the Bi2-xPbxSr2Ca2-yCuyOz system, with predictions closely aligning with experimental results. Leveraging this model, we screen compounds from the Inorganic Crystal Structure Database and employ a generative approach to explore new doped superconductors. This process reveals 40 promising candidates for high Tc superconductivity among existing and hypothetical doped materials. By explicitly accounting for doping effects, our method offers a powerful tool for guiding the experimental discovery of new superconductors, potentially accelerating progress in high-temperature superconductivity research and opening new avenues for material design.

Exploring the potential of Sn-Ge based hybrid organic-inorganic perovskites: A density functional theory based computational screening study

Hybrid organic-inorganic perovskite solar cells have attracted significant attention in the field of optoelectronics due to their exceptional photovoltaic and optoelectronic properties. Although lead (Pb)-based perovskites exhibit the highest power conversion efficiencies, concerns about their toxicity and environmental impact have prompted significant research activities to explore alternative compositions. In this regard, a special emphasis has been devoted to tin (Sn) and germanium (Ge) based perovskites. In order to reveal the full potential of Sn-Ge based perovskites, we computationally screened perovskites with a general formula of A0.5A0.5'SnyGe1-yX3 (y = 0.00, 0.25, 0.50, 0.75, 1.00) at the density functional theory level, particularly using the HSE06 hybrid functional. By using 18 A/A'-cations, four X-anions, and five different y compositions, a total of 7695 perovskites in cubic (C), orthogonal (O), and tetragonal (T) phases were considered, and the most promising ones have been filtered out based on their formation energy and bandgap. More specifically, 596, 525, and 542 C-, O-, and T-phase perovskites have been identified with a HSE06 bandgap range of 1.0-2.0 eV. While the Sn1.00Ge0.00 composition was dominated for both C- and O-phases, for the T-phase, a higher number of promising perovskites were obtained with the Sn0.75Ge0.25 composition. It has also been found that Sn-rich perovskites exhibit more favorable bandgap characteristics compared to Ge-rich ones. FA, MS, MA, K, Cs, and Rb are the most favored A/A'-cations in these promising perovskites. Moreover, I- overwhelmingly prevails as the dominant anion. Further experimental validation may uncover the true capabilities and practical applicability of these promising perovskites.

MatGPT: A Vane of Materials Informatics from Past, Present, to Future

Combining materials science, artificial intelligence (AI), physical chemistry, and other disciplines, materials informatics is continuously accelerating the vigorous development of new materials. The emergence of "GPT (Generative Pre-trained Transformer) AI" shows that the scientific research field has entered the era of intelligent civilization with "data" as the basic factor and "algorithm + computing power" as the core productivity. The continuous innovation of AI will impact the cognitive laws and scientific methods, and reconstruct the knowledge and wisdom system. This leads to think more about materials informatics. Here, a comprehensive discussion of AI models and materials infrastructures is provided, and the advances in the discovery and design of new materials are reviewed. With the rise of new research paradigms triggered by "AI for Science", the vane of materials informatics: "MatGPT", is proposed and the technical path planning from the aspects of data, descriptors, generative models, pretraining models, directed design models, collaborative training, experimental robots, as well as the efforts and preparations needed to develop a new generation of materials informatics, is carried out. Finally, the challenges and constraints faced by materials informatics are discussed, in order to achieve a more digital, intelligent, and automated construction of materials informatics with the joint efforts of more interdisciplinary scientists.

CEEM: a Chemically Explainable Deep Learning Platform for Identifying Compounds with Low Effective Mass

The semiconductor industry occupies a crucial position in the fields of integrated circuits, energy, and communication systems. Effective mass (mE ), which is closely related to electron transition, thermal excitation, and carrier mobility, is a key performance indicator of semiconductor. However, the highly neglected mE is onerous to measure experimentally, which seriously hinders the evaluation of semiconductor properties and the understanding of the carrier migration mechanisms. Here, a chemically explainable effective mass predictive platform (CEEM) is constructed by deep learning, to identify n-type and p-type semiconductors with low mE . Based on the graph network, a versatile explainable network is innovatively designed that enables CEEM to efficiently predict the mE of any structure, with the area under the curve of 0.904 for n-type semiconductors and 0.896 for p-type semiconductors, and derive the most relevant chemical factors. Using CEEM, the currently largest mE database is built that contains 126 335 entries and screens out 466 semiconductors with low mE for transparent conductive materials, photovoltaic materials, and water-splitting materials. Moreover, a user-friendly and interactive CEEM web is provided that supports query, prediction, and explanation of mE . CEEM's high efficiency, accuracy, flexibility, and explainability open up new avenues for the discovery and design of high-performance semiconductors.

Feature Selection in Machine Learning for Perovskite Materials Design and Discovery

Perovskite materials have been one of the most important research objects in materials science due to their excellent photoelectric properties as well as correspondingly complex structures. Machine learning (ML) methods have been playing an important role in the design and discovery of perovskite materials, while feature selection as a dimensionality reduction method has occupied a crucial position in the ML workflow. In this review, we introduced the recent advances in the applications of feature selection in perovskite materials. First, the development tendency of publications about ML in perovskite materials was analyzed, and the ML workflow for materials was summarized. Then the commonly used feature selection methods were briefly introduced, and the applications of feature selection in inorganic perovskites, hybrid organic-inorganic perovskites (HOIPs), and double perovskites (DPs) were reviewed. Finally, we put forward some directions for the future development of feature selection in machine learning for perovskite material design.

Materials Discovery With Machine Learning and Knowledge Discovery

Machine learning and other artificial intelligence methods are gaining increasing prominence in chemistry and materials sciences, especially for materials design and discovery, and in data analysis of results generated by sensors and biosensors. In this paper, we present a perspective on this current use of machine learning, and discuss the prospects of the future impact of extending the use of machine learning to encompass knowledge discovery as an essential step towards a new paradigm of machine-generated knowledge. The reasons why results so far have been limited are given with a discussion of the limitations of machine learning in tasks requiring interpretation. Also discussed is the need to adapt the training of students and scientists in chemistry and materials sciences, to better explore the potential of artificial intelligence capabilities.

Simple Structural Descriptor Obtained from Symbolic Classification for Predicting the Oxygen Vacancy Defect Formation of Perovskites

Symbolic classification is an approach of interpretable machine learning for building mathematical formulas that fit certain data sets. In this work, symbolic classification is used to establish the relationship between oxygen vacancy defect formation energy and structural features. We find a structural descriptor n_a(r_a/E_na - r_b), where n_a is the valence of the a-site ion, r_a is the radius of the a-site ion, E_na is the electronegativity of the a-site ion, and r_b is the radius of the b-site ion. It accelerates the screening of defect-free oxide perovskites in advance of density functional theory (DFT) calculations and experimental characterization. Our results demonstrate the potential of symbolic classification for accelerating the data-driven design and discovery of materials with improved properties.