One of the most challenging and significant objectives of NASA over the coming years is to successfully send humans to Mars. The past six decades of safety concerns addressed for satellite and rover missions, become an even more important consideration with human passengers. Atmospheric and surface conditions of Mars can change abruptly, leading to communication breaks, equipment failures, and potential safety threats. The sudden onset of a dust storm, or a more common dust devil, can interfere with atmospheric entry, ground mechanical equipment, solar charging systems, and much more. By combining traditional signal processing techniques and with an efficient machine learning algorithm, this paper proposes to classify atmospheric disturbances on the red planet with a high level of accuracy.