Characterization of microalgae cultures is a critical task in optimizing the operation and quality control of microalgae cultures. This task has traditionally been performed manually by qualified laboratory personnel using a microscope. This methodology is inefficient, time-consuming, and requires specialized personnel, which has motivated considerable research efforts for the development of more automated solutions. The present chapter presents different methods for approaching the classification of microalgae cultures based on machine learning and, more specifically, artificial neural networks. This set of techniques uses descriptive data from the culture, such as microscopic images, spectral sweeps, and cytometries, to extract information that often transcends human perception. In this way, they are able to infer hidden patterns in the data, learning from these in an automatic way to develop models that allow their characterization. The techniques presented offer high classification accuracy, replacing the need for manual and slow methods with fast and easy-to-apply approaches.