packages = ['pandas', 'joblib','scikit-learn','bokeh'] [[fetch]] from = 'https://raw.githubusercontent.com/cmd-ml/iiiv.eg.zb.github.io/main/Ridge_Eg.pkl' name = 'eg' [[fetch]] from = 'https://raw.githubusercontent.com/cmd-ml/iiiv.eg.zb.github.io/main/Ridge_Ex.pkl' name = 'ex'

Bandgap Energy Predictor of III-V Senary Zincblende Compounds:
Machine Learning Model

Please cite:
- Mohammad Alsalman et. al., “Bandgap Energy Prediction of Senary Zincblende III-V Semiconductor Compounds using Machine Learning,” Materials Science in Semiconductor Processing, vol. 161, p. 107461, 2023.

User Guide:

- Please wait for around 30 seconds until the webpage is loaded.
- If the website is not responding, please try to open the website using different web browser.
- If the website is not responding, please try opening it using a different web browser or check if your Internet service provider is blocking the application's executable segment.
- The figure of the predicted energy bandgap will appear after pressing the "Plot" button.
- Set of examples: GaAs, Al0.5Ga0.5As, InP0.5As0.5, Al0.2Ga0.6In0.2P0.3As0.7, Al0.14Ga0.5In0.36P0.328As0.242Sb0.430.
- For plotting, only single variation will be plotted based on your inputs. Criteria are as follows:
i - If the initial compound is GaAs and the final compound is AlAs, it varies the molarity of Ga and Al.
ii - If the initial compound is Al0.3Ga0.7As and the final compound is Al0.3Ga0.7Sb, it varies the molarity of As and Sb.
iii - If the initial compound is Al0.2Ga0.6In0.2P0.3As0.7 and the final compound is Al0.6Ga0.2In0.2P0.3As0.7, it varies the molarity of Al and Ga from the initial fraction to the final fraction of these two elements.

Please click on the type of prediction:

©2025 cmd-ml Group. (ver. 25.1)

Type the compound of interest: Configuration: Alx1Gax2Inx3Py1Asy2Sby3
For example, Al0.5Ga0.5As

Type the initial compound: Configuration: Alx1Gax2Inx3Py1Asy2Sby3
For example, GaAs



Type the final compound: Configuration: Alx1Gax2Inx3Py1Asy2Sby3
For example, AlAs

.