A method, apparatus and computer program product are provided to predict a map object based at least in part on audio data. With respect to predicting a map object, audio data created by a vehicle while driving over a road surface is obtained. The audio data includes one or more audio amplitude features, one or more audio frequency features or a combination of audio amplitude features and audio frequency features. The audio data including the one or more audio amplitude features is provided to a machine learning model and the map object that created the audio data while the vehicle interacted therewith is predicted utilizing the machine learning model. A method, apparatus and computer program product are also provided for training the machine learning model to predict the map object based at least in part on audio data.