Search

Growth of high-quality single crystals is of great significance for research of condensed matter physics. The exploration of suitable growing conditions for single crystals is expensive and time-consuming, especially for ternary compounds because of the lack of ternary phase diagram. Here we use machine learning (ML) trained on our experimental data to predict and instruct the growth. Four kinds of ML methods, including support vector machine (SVM), decision tree, random forest and gradient boosting decision tree, are adopted. The SVM method is relatively stable and works well, with an accuracy of 81% in predicting experimental results. By comparison, the accuracy of laboratory reaches 36%. The decision tree model is also used to reveal which features will take critical roles in growing processes. [ABSTRACT FROM AUTHOR]

We report the growth process of FeTe1−xSex () monolayer films on SrTiO3(STO) substrates through molecular beam epitaxy and discuss the possible ways to improve the film quality. By exploring the parameters of substrate treatment, growth control and post growth annealing, we successfully obtain a series of FeTe1−xSex monolayer films. In the whole growth process, we find the significance of the temperature control through surface roughness monitored by the reflection high-energy electron diffraction and scanning tunneling microscopy. We obtain the best quality of FeSe monolayer films with the STO substrate treated at T = 900–950°C before growth, the FeSe deposited at T = 310°C during growth and annealed at T = 380°C after growth. For FeTe1−xSex (), both the growth temperature and annealing temperature decrease to T = 260°C. According to the angle-resolved photoemission spectroscopy measurements, the superconductivity of the FeTe1−xSex film is robust and insensitive to Se concentration. All the above are instructive for further investigations of the superconductivity in FeTe1−xSex films. [ABSTRACT FROM AUTHOR]