光催化
计算机科学
关系(数据库)
人工智能
沉思
信息学
鉴定(生物学)
工程类
化学
数据挖掘
认识论
电气工程
哲学
生物
催化作用
植物
生物化学
作者
Tulsi Satyavir Dabodiya,Jayant Kumar,Arumugam Vadivel Murugan
出处
期刊:Springer eBooks
[Springer Nature]
日期:2023-01-01
卷期号:: 221-232
被引量:3
标识
DOI:10.1007/978-981-99-0393-1_10
摘要
Advancement of technology in the current era of the Internet of things (IoT) and artificial intelligence (AI) has made researchers to explore into the subfield of data science identified as the Machine Learning (ML). Utilization of ML could benefit the research community for various applications. Coupling of ML with a photocatalyst (PC) can accelerate the facile understanding of the relation between the structure-property-application-oriented relation with its practical application in the areas of sustainable hydrogen generation by water splitting reaction and environmental remediation. Machine learning can be considered as a remarkable tool for unveiling the large knowledge pool related to improvising the efficiency of the photocatalyst. Herein, in this chapter, we aim to provide a brief introduction into the ML process that could benefit the photocatalysis field. Further, the chapter provides basic PC research knowledge that could potentially be useful for machine learning methods. Additionally, we also describe the pre-existing ML practices in PC are for quick identification of novel photocatalysts. Finally, the available conceptualized strategies for complementing data-driven ML with PC are elaborated. The chapter would thereby imbibe the need for utilizing existing databases for investing in the ML training and predictions. This chapter aims to provide adequate information regarding photocatalyst informatics together with the Edisonian approach. Eventually, the chapter demonstrates the potential and need for machine learning to accelerate the discovery of novel photocatalysts.
科研通智能强力驱动
Strongly Powered by AbleSci AI