Historical Data Mining Deep Dive into Machine Learning-Aided 2D Materials Research in Electrochemical Applications.

Area of Science:

• Materials Science
• Computational Chemistry
• Electrochemistry

Background:

• Machine learning (ML) is revolutionizing 2D materials design.
• ML accelerates discovery, optimization, and screening processes.
• Integration of ML in 2D materials for electrochemical energy applications is a growing field.

Purpose of the Study:

• To review the historical and ongoing integration of ML in 2D materials for electrochemical energy applications.
• To analyze trends and insights using the Knowledge Discovery in Databases (KDD) approach.
• To highlight the synergy between ML, density functional theory (DFT), and experimentation.

Main Methods:

• Data mining from the Scopus database.
• Analysis of citations, keywords, and trends.
• Computer analysis of literature reports (heat maps, network graphs) for macro and micro scope insights.

Main Results:

• Identified key insights from large-scale literature analysis.
• Showcased ML techniques for identifying critical material properties.
• Demonstrated the joint advancement of materials science through ML, DFT, and experimentation.

Conclusions:

• ML, DFT, and traditional experimentation are collectively driving progress in 2D materials for energy applications.
• This review provides a comprehensive analysis of ML applications in batteries, fuel cells, supercapacitors, and synthesis.
• ML is crucial for enhancing the identification of essential material properties.