If we know something about the physics of the data generation process, we can use that information to construct a model. For example, in speech-related applications, knowledge about the physics of speech production can be used to construct a mathematical model for the sampled speech process. Sampled speech can then be encoded using this model
Models for certain telemetry data can also be obtained through knowledge of the underlying process. For example, if residential electrical meter readings at hourly intervals were to be coded, knowledge about the living habits of the populace could be used to determine when electricity usage would be high and when the usage would be low. Then instead of the actual readings, the difference (residual) between the actual readings and those predicted by the model could be coded.
In general, however, the physics of data generation is simply too complicated to understand, let alone use to develop a model. Where the physics of the problem is too complicated, we can obtain a model based on empirical observation of the statistics of the data.