The increased use of Artificial Intelligence (AI) in everyday life has inspired applications across many scientific disciplines, one of which is the study of stellar oscillations - asteroseismology. The frequency spectra and identification of pulsational modes in stars offer important insights into their internal structure and the evolution of these objects throughout different stages of their lives. In this master’s thesis, we develop a machine learning framework that can identify the oscillation modes in pulsating pre-main sequence stars given their oscillation frequencies. With a grid simulated using the stellar evolution code MESA and the stellar oscillation code GYRE, we obtain simulated frequency spectra for a range of pre-main sequence models. From these frequencies, so-called échelle diagrams are generated, which provide a way to identify different angular pulsational modes. It is shown that a simple neural network architecture can be trained on the simulated data to accurately identify the ridges and their corresponding angular mode numbers within the échelle diagrams. This approach illustrates the power of AI and neural networks in particular when it comes to applications in asteroseismic analysis, potentially opening new doors for mode identification of oscillating stars with upcoming missions such as PLATO (PLAnetaryTransits and Oscillations of stars).