Browsing by Author "Yang, ZW"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Data quantity governance for machine learning in materials science
    (Oxford University Press (OUP), 2023-05-31) Liu, Y; Yang, ZW; Zou, XX; Ma, S; Liu, D; Avdeev, M; Shi, S
    Data-driven machine learning (ML) is widely employed in the analysis of materials structure–activity relationships, performance optimization and materials design due to its superior ability to reveal latent data patterns and make accurate prediction. However, because of the laborious process of materials data acquisition, ML models encounter the issue of the mismatch between a high dimension of feature space and a small sample size (for traditional ML models) or the mismatch between model parameters and sample size (for deep-learning models), usually resulting in terrible performance. Here, we review the efforts for tackling this issue via feature reduction, sample augmentation and specific ML approaches, and show that the balance between the number of samples and features or model parameters should attract great attention during data quantity governance. Following this, we propose a synergistic data quantity governance flow with the incorporation of materials domain knowledge. After summarizing the approaches to incorporating materials domain knowledge into the process of ML, we provide examples of incorporating domain knowledge into governance schemes to demonstrate the advantages of the approach and applications. The work paves the way for obtaining the required high-quality data to accelerate materials design and discovery based on ML. © The Author(s) 2023. Published by Oxford University Press on behalf of China Science Publishing & Media Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
  • No Thumbnail Available
    Item
    Domain knowledge discovery from abstracts of scientific literature on Nickel-based single crystal superalloys
    (Springer Nature, 2023-04-27) Liu, Y; Ding, L; Yang, ZW; Ge, XY; Liu, DH; Liu, W; Yu, T; Avdeev, M; Shi, SQ
    Despite the huge accumulation of scientific literature, it is inefficient and laborious to manually search it for useful information to investigate structure-activity relationships. Here, we propose an efficient text-mining framework for the discovery of credible and valuable domain knowledge from abstracts of scientific literature focusing on Nickel-based single crystal superalloys. Firstly, the credibility of abstracts is quantified in terms of source timeliness, publication authority and author’s academic standing. Next, eight entity types and domain dictionaries describing Nickel-based single crystal superalloys are predefined to realize the named entity recognition from the abstracts, achieving an accuracy of 85.10%. Thirdly, by formulating 12 naming rules for the alloy brands derived from the recognized entities, we extract the target entities and refine them as domain knowledge through the credibility analysis. Following this, we also map out the academic cooperative “Author-Literature-Institute” network, characterize the generations of Nickel-based single crystal superalloys, as well as obtain the fractions of the most important chemical elements in superalloys. The extracted rich and diverse knowledge of Nickel-based single crystal superalloys provides important insights toward understanding the structure-activity relationships for Nickel-based single crystal superalloys and is expected to accelerate the design and discovery of novel superalloys. © Science China Press. © 2024 Springer Nature.
  • No Thumbnail Available
    Item
    Generative artificial intelligence and its applications in materials science: current situation and future perspectives
    (Elsevier, 2023-07) Liu, Y; Yang, ZW; Yu, ZY; Liu, Z; Liu, D; Lin, H; Li, MQ; Ma, S; Avdeev, M; Shi, SQ
    Generative Artificial Intelligence (GAI) is attracting the increasing attention of materials community for its excellent capability of generating required contents. With the introduction of Prompt paradigm and reinforcement learning from human feedback (RLHF), GAI shifts from the task-specific to general pattern gradually, enabling to tackle multiple complicated tasks involved in resolving the structure-activity relationships. Here, we review the development status of GAI comprehensively and analyze pros and cons of various generative models in the view of methodology. The applications of task-specific generative models involving materials inverse design and data augmentation are also dissected. Taking ChatGPT as an example, we explore the potential applications of general GAI in generating multiple materials content, solving differential equation as well as querying materials FAQs. Furthermore, we summarize six challenges encountered for the use of GAI in materials science and provide the corresponding solutions. This work paves the way for providing effective and explainable materials data generation and analysis approaches to accelerate the materials research and development. © 2023 The Authors. Published by Elsevier B.V. on behalf of The Chinese Ceramic Society. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).