Solar panel improvement

We use the state of the art machine learning methods to improve solar panel designs. Greve et al. have recently shown that adding nano-particles to solar panels can increase their efficiency. However, there are many possible configurations how the nano-particles can be added to the solar panels and time-consuming physics modeling is necessary to optimize the design. We will initially explore a 2-dimensional parameter space of nano-particle configurations and design a machine learning model that predicts the light spectrum the solar panel can capture. Then we use this machine learning model to optimize the parameters. Extensions of the project will involve optimizing a more complex higher-dimensional parameter space.