Gravitational waves are an exceptional opportunity for studying and interpreting phenomena from the universe. Automatic signal processing and machine learning techniques can provide significant support for the efficient detection and analysis of gravitational waves from large-scale data continuously collected by interferometers. This chapter discusses two approaches involving deep auto-encoder models to analyze and classify raw time series data into noise or gravitational waves. The goal is to provide astrophysicists with a tool that can quickly discard noisy time series and identify time series that potentially contain an actual astrophysical phenomenon. Experiments carried out on three datasets show that the discussed approaches implemented in a scalable manner using Apache Spark represent a valuable machine learning approach for astrophysical analysis, offering competitive accuracy compared to state-of-the-art methods.