Infrasound is low frequency sound that falls below the range of typical human hearing (< 20 Hz). It is generated by both natural and anthropogenic sources such as chemical and nuclear explosions, volcanic eruptions, and earthquakes. Understanding the path an infrasound wave takes through the atmosphere is important for both predicting and understanding when signals will arrive following an event of interest. Temperature and wind profiles are essential for accurately modeling the wave’s path, but an easily portable model does not yet exist. We present a new and portable deep learning model that can generate and predict weather profiles for infrasound modeling. We compare this model to the current state-of-the-art and show how it can be used as part of an analysis pipeline.