Machine learning enabled electronic band-edge shapes and properties prediction of 2D transition metal dichalcogenide alloys

Key Points

• This research aims to develop machine learning models for predicting electronic properties of 2D transition metal dichalcogenide alloys.
• Utilized machine learning algorithms to model electronic band-edge properties.
• Compared predictions with traditional density functional theory calculations.
• Analyzed the efficiency of data-driven approaches versus conventional methods.
• Machine learning models achieved comparable accuracy to DFT while significantly reducing computation time.
• Predictions indicate potential for rapid screening of new 2D materials.
• Findings underscore the viability of data-driven techniques in materials science.