计算机科学
资源(消歧)
领域(数学)
可再生能源
储能
系统工程
风险分析(工程)
纳米技术
数据科学
生化工程
管理科学
工程类
电气工程
材料科学
医学
计算机网络
功率(物理)
物理
数学
量子力学
纯数学
作者
Prit Thakkar,Samantha I. Khatri,Drashti Dobariya,Darpan I. Patel,Bishwajit Dey,Alok Kumar Singh
标识
DOI:10.1016/j.est.2024.110452
摘要
The increasing global need for energy supply in modern society has created a pressing need to explore new materials for renewable energy technologies. However, conventional trial and error methods in materials science are often tedious as well as costly, making it challenging to meet the growing demands. In recent years, machine learning (ML) become a prominent research strategy transfigure the discovery of materials. This review offers a concise summary of the elementary ML procedures and widely used algorithms in the field of materials science. It particularly emphasizes the latest advancements in utilizing ML for predicting material properties and developing materials for energy-related fields like Li-Ion batteries, Super-Capacitors, and Hybrid Systems. Furthermore, the review discusses the contributions of ML to experimental research. This review intents to serve as a guiding resource for future developments of ML in materials science.
科研通智能强力驱动
Strongly Powered by AbleSci AI