This work connects atomistic modeling of double nanowire quantum dots with machine-learning-assisted prediction of spectral properties. It illustrates how data-driven tools can accelerate exploration of high-dimensional nanostructure parameter spaces.
Keywords: nanowire quantum dots, machine learning
Main result: machine learning can be trained on atomistic simulations to predict spectral trends in double nanowire quantum dots. This opens a path toward faster screening and inverse design of coupled nanostructures.