Effective combinations of features in predicting the range of incident ions using machine learning

Abstract

Machine learning techniques were used to predict the range of ions in material, even when stopping power data is unknown. Simple features such as atomic and mass numbers were used in learning process. Two different machine learning models, Decision Tree (DT) and Kernel Ridge Regression (KRR), were used to assess each feature’s importance and the effect of combining them. The results showed that the chosen features were sufficient for accurate prediction. Furthermore, it was found that the combination and features are essential for accurate results. Analysis by KRR established a relationship between the range of the implanted ions and the energy of the incident ions, showing that the range is approximately proportional to the energy in the dataset used in this work.