Materials descriptors of machine learning to boost development of lithium-ion batteries

IF 13.4 2区材料科学 Q1 MATERIALS SCIENCE, MULTIDISCIPLINARY

Nano Convergence Pub Date : 2024-02-26 DOI:10.1186/s40580-024-00417-6

Zehua Wang, Li Wang, Hao Zhang, Hong Xu, Xiangming He

{"title":"Materials descriptors of machine learning to boost development of lithium-ion batteries","authors":"Zehua Wang, Li Wang, Hao Zhang, Hong Xu, Xiangming He","doi":"10.1186/s40580-024-00417-6","DOIUrl":null,"url":null,"abstract":"<div><p>Traditional methods for developing new materials are no longer sufficient to meet the needs of the human energy transition. Machine learning (ML) artificial intelligence (AI) and advancements have caused materials scientists to realize that using AI/ML to accelerate the development of new materials for batteries is a powerful potential tool. Although the use of certain fixed properties of materials as descriptors to act as a bridge between the two separate disciplines of AI and materials chemistry has been widely investigated, many of the descriptors lack universality and accuracy due to a lack of understanding of the mechanisms by which AI/ML operates. Therefore, understanding the underlying operational mechanisms and learning logic of AI/ML has become mandatory for materials scientists to develop more accurate descriptors. To address those challenges, this paper reviews previous work on AI, machine learning and materials descriptors and introduces the basic logic of AI and machine learning to help materials developers understand their operational mechanisms. Meanwhile, the paper also compares the accuracy of different descriptors and their advantages and disadvantages and highlights the great potential value of accurate descriptors in AI/machine learning applications for battery research, as well as the challenges of developing accurate material descriptors.</p><h3>Graphical Abstract</h3>\n<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":712,"journal":{"name":"Nano Convergence","volume":"11 1","pages":""},"PeriodicalIF":13.4000,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://nanoconvergencejournal.springeropen.com/counter/pdf/10.1186/s40580-024-00417-6","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nano Convergence","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1186/s40580-024-00417-6","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Traditional methods for developing new materials are no longer sufficient to meet the needs of the human energy transition. Machine learning (ML) artificial intelligence (AI) and advancements have caused materials scientists to realize that using AI/ML to accelerate the development of new materials for batteries is a powerful potential tool. Although the use of certain fixed properties of materials as descriptors to act as a bridge between the two separate disciplines of AI and materials chemistry has been widely investigated, many of the descriptors lack universality and accuracy due to a lack of understanding of the mechanisms by which AI/ML operates. Therefore, understanding the underlying operational mechanisms and learning logic of AI/ML has become mandatory for materials scientists to develop more accurate descriptors. To address those challenges, this paper reviews previous work on AI, machine learning and materials descriptors and introduces the basic logic of AI and machine learning to help materials developers understand their operational mechanisms. Meanwhile, the paper also compares the accuracy of different descriptors and their advantages and disadvantages and highlights the great potential value of accurate descriptors in AI/machine learning applications for battery research, as well as the challenges of developing accurate material descriptors.

Graphical Abstract

查看原文本刊更多论文

利用机器学习的材料描述符促进锂离子电池的开发

开发新材料的传统方法已不足以满足人类能源转型的需求。机器学习（ML）人工智能（AI）的发展和进步使材料科学家意识到，利用 AI/ML 加速开发新的电池材料是一种强大的潜在工具。虽然利用材料的某些固定属性作为描述符来充当人工智能和材料化学这两个独立学科之间的桥梁已得到广泛研究，但由于缺乏对人工智能/ML 运行机制的了解，许多描述符缺乏普遍性和准确性。因此，材料科学家必须了解人工智能/ML 的基本运行机制和学习逻辑，才能开发出更准确的描述符。为了应对这些挑战，本文回顾了以往有关人工智能、机器学习和材料描述符的研究工作，并介绍了人工智能和机器学习的基本逻辑，以帮助材料开发人员了解其运行机制。同时，本文还比较了不同描述符的准确性及其优缺点，强调了准确描述符在人工智能/机器学习应用于电池研究方面的巨大潜在价值，以及开发准确材料描述符所面临的挑战。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Nano Convergence Engineering-General Engineering

CiteScore

15.90

自引率

2.60%

发文量

审稿时长

13 weeks

期刊介绍： Nano Convergence is an internationally recognized, peer-reviewed, and interdisciplinary journal designed to foster effective communication among scientists spanning diverse research areas closely aligned with nanoscience and nanotechnology. Dedicated to encouraging the convergence of technologies across the nano- to microscopic scale, the journal aims to unveil novel scientific domains and cultivate fresh research prospects. Operating on a single-blind peer-review system, Nano Convergence ensures transparency in the review process, with reviewers cognizant of authors' names and affiliations while maintaining anonymity in the feedback provided to authors.