Machine-Learning Assisted First-Principles Model Development to Interpret ARPES Data and Assist Inverse Design of Heterostructures

Advances of nanofabrication techniques have achieved great control over the growth of semiconductor heterostructures. Nevertheless, fabrication of heterostructures is strongly affected by strain environent in component layers, and the resulting electronic properties show high variability. The layer compositions and external substrate induced strains prompt non-uniform separations between monolayers and modulate electronic properties. It remains a challenge to model electronic transport coefficients of technologically relevant heterostructures incorporatingfull structural complexity, representing the vast fabrication dependent structural parameterspace. On the other hand, characterization techniques like the angle-resolved photoemission spectroscopy (ARPES) provides great insight regarding the nature of electronic bands. We establish a convolutional neural network based autoencoder that can extract infomation from ARPES images and use first principles data to predict electronic properties of fabricated heterostructures.