Knowledge-reused transfer learning for molecular and materials science

Leveraging big data analytics and advanced algorithms to accelerate and optimize the process of molecular and materials design, synthesis, and application has revolutionized the field of molecular and materials science, allowing researchers to gain a deeper understanding of material properties and behaviors,leading to the development of new materials that are more efficient and reliable. However, the difficulty in constructing large-scale datasets of new molecules/materials due to the high cost of data acquisition and annotation limits the development of conventional machine learning(ML) approaches. Knowledgereused transfer learning(TL) methods are expected to break this dilemma. The application of TL lowers the data requirements for model training, which makes TL stand out in researches addressing data quality issues. In this review, we summarize recent progress in TL related to molecular and materials. We focus on the application of TL methods for the discovery of advanced molecules/materials, particularly, the construction of TL frameworks for different systems, and how TL can enhance the performance of models. In addition, the challenges of TL are also discussed.

Literature classification and its applications in condensed matter physics and materials science by natural language processing

The exponential growth of literature is constraining researchers’access to comprehensive information in related fields.While natural language processing(NLP)may offer an effective solution to literature classification,it remains hindered by the lack of labelled dataset.In this article,we introduce a novel method for generating literature classification models through semi-supervised learning,which can generate labelled dataset iteratively with limited human input.We apply this method to train NLP models for classifying literatures related to several research directions,i.e.,battery,superconductor,topological material,and artificial intelligence(AI)in materials science.The trained NLP‘battery’model applied on a larger dataset different from the training and testing dataset can achieve F1 score of 0.738,which indicates the accuracy and reliability of this scheme.Furthermore,our approach demonstrates that even with insufficient data,the not-well-trained model in the first few cycles can identify the relationships among different research fields and facilitate the discovery and understanding of interdisciplinary directions.

MatChat: A large language model and application service platform for materials science

The prediction of chemical synthesis pathways plays a pivotal role in materials science research. Challenges, such as the complexity of synthesis pathways and the lack of comprehensive datasets, currently hinder our ability to predict these chemical processes accurately. However, recent advancements in generative artificial intelligence(GAI), including automated text generation and question–answering systems, coupled with fine-tuning techniques, have facilitated the deployment of large-scale AI models tailored to specific domains. In this study, we harness the power of the LLaMA2-7B model and enhance it through a learning process that incorporates 13878 pieces of structured material knowledge data.This specialized AI model, named Mat Chat, focuses on predicting inorganic material synthesis pathways. Mat Chat exhibits remarkable proficiency in generating and reasoning with knowledge in materials science. Although Mat Chat requires further refinement to meet the diverse material design needs, this research undeniably highlights its impressive reasoning capabilities and innovative potential in materials science. Mat Chat is now accessible online and open for use, with both the model and its application framework available as open source. This study establishes a robust foundation for collaborative innovation in the integration of generative AI in materials science.

Molecular Dynamics (MD) Applications in Materials Science and Engineering and Nanotechnology

Molecular dynamics (MD) is a computer simulation technique that helps to explore the behavior and properties of molecules and atoms. MD has been used in research and development in many spaces, including materials science and engineering and nanotechnology. MD has been proven useful in topics like the nano-engineering of construction materials, correcting graphene planar defects, studying self-assembling bio-materials, and the densification, consolidation, and sintering of nanocrystalline materials.

Development of advanced electron tomography in materials science based on TEM and STEM

The recent developments of electron tomography（ET） based on transmission electron microscopy（TEM） and scanning transmission electron microscopy（STEM） in the field of materials science were introduced. The various types of ET based on TEM as well as STEM were described in detail, which included bright-field（BF）-TEM tomography, dark-field（DF）-TEM tomography, weak-beam dark-field（WBDF）-TEM tomography, annular dark-field（ADF）-TEM tomography, energy-filtered transmission electron microscopy（EFTEM） tomography, high-angle annular dark-field（HAADF）-STEM tomography, ADF-STEM tomography, incoherent bright field（IBF）-STEM tomography, electron energy loss spectroscopy（EELS）-STEM tomography and X-ray energy dispersive spectrometry（XEDS）-STEM tomography, and so on. The optimized tilt series such as dual-axis tilt tomography, on-axis tilt tomography, conical tilt tomography and equally-sloped tomography（EST） were reported. The advanced reconstruction algorithms, such as discrete algebraic reconstruction technique（DART）, compressed sensing（CS） algorithm and EST were overviewed. At last, the development tendency of ET in materials science was presented.

Recent Progress in Space Science and Applications on Chinese Space Station in 2022–2024

Chinese Space Station(CSS)has been fully deployed by the end of 2022,and the facility has entered into the application and development phase.It has conducted scientific research projects in various fields,such as space life science and biotechnology,space materials science,microgravity fundamental physics,fluid physics,combustion science,space new technologies,and applications.In this review,we introduce the progress of CSS development and provide an overview of the research conducted in Chinese Space Station and the recent scientific findings in several typical research fields.Such compelling findings mainly concern the rapid solidification of ultra-high temperature alloy melts,dynamics of fluid transport in space,gravity scaling law of boiling heat transfer,vibration fluidization phenomenon of particulate matter,cold atom interferometer technology under high microgravity and related equivalence principle testing,the full life cycle of rice under microgravity and so forth.Furthermore,the planned scientific research and corresponding prospects of Chinese space station in the next few years are presented.

人工智能背景下Materials Project数据库在计算材料学课程教学中的应用

该文探讨了在人工智能背景下,Materials Project数据库在计算材料学课程教学中的应用和影响。Materials Project数据库是一个集成了AI和大数据技术的开放获取的材料库,能为学生提供海量的材料晶体结构和物性数据,使教学内容更为丰富,让学生能通过亲自操作获取和分析数据,深入理解微观结构与物性之间的关系。这一新兴的教学模式不仅提升了学生的科研能力和创新思维能力,还有助于培养具备计算材料专业知识和多学科交叉的复合型人才。总体来说,人工智能时代下,大数据的引入为计算材料学课程带来新的活力,并对未来教育改革和实践产生了积极影响。

SPACE MATERIALS SCIENCE

The main studying activities and results on space materials science during 1996-1997 in China were summarized. The typical research subjects are crystal growth from melt, crystal growth from solution, nucleation, undercooling,solidification of alloys and space experimental hardware. They are carried out by the ground-based studies, the short duration microgravity missions and orbital experiments.

The materials data ecosystem： Materials data science and its role in data-driven materials discovery

Since its launch in 2011, the Materials Genome Initiative（MGI） has drawn the attention of researchers from academia,government, and industry worldwide. As one of the three tools of the MGI, the use of materials data, for the first time, has emerged as an extremely significant approach in materials discovery. Data science has been applied in different disciplines as an interdisciplinary field to extract knowledge from data. The concept of materials data science has been utilized to demonstrate its application in materials science. To explore its potential as an active research branch in the big data era, a three-tier system has been put forward to define the infrastructure for the classification, curation and knowledge extraction of materials data.

Technical Note and Brief Overview of the Materials Science and Technology along with Designing Aspects for Development of Spintronic Devices with Optimum Efficiency

One of the major challenges in designing and fabricating Spintronic devices is the choice of both, Materials and the Technology, along with understanding the intricacies of the Designing aspects. In this communication, we have attempted to briefly discuss these factors, with an aim to draw the attention of the Materials Scientists and Technologists to this serious challenge, in the direction of which, though a lot of research and development work has been done, still needs more concerted efforts to be made in order to make the Spintronic devices that can offer good efficiency for maximizing their usefulness.

Progress of Materials Science in Space Technology in China(2020-2022)

In this paper,the main research work and related reports of materials science research in China’s space technology field during 2020-2022 are summarized.This paper covers Materials Sciences in Space Environment,Materials Sciences for Space Environment,Materials Behavior in Space Environment and Space experimental hardware for material investigation.With the rapid development of China’s space industry,more scientists will be involved in materials science,space technology and earth science researches.In the future,a series of disciplines such as space science,machinery,artificial intelligence,digital twin and big data will be further integrated with materials science,and space materials will also usher in new development opportunities.