In an embodiment, the machine learning component 106 can predict the one or more characteristics associated with the one or more 3D models based on input data and one or more machine learning processes associated with the one or more 3D models. The input data can be, for example, a set of parameters for a fluid capable of flowing through the one or more 3D models, a set of parameters for a thermal energy capable of flowing through the one or more 3D models, a set of parameters for a combustion chemical reaction capable of flowing through the one or more 3D models, a set of parameters for electricity flowing through the one or more 3D models, and/or another set of parameters for input provided to the one or more 3D models. The one or more characteristics associated with the one or more 3D models can correspond to one or more characteristics of the device (e.g., the mechanical device and/or the electronic device). In one example, distinct types of control volumes (e.g., chambers) simulating reservoirs, volume mixing dynamics, volume inertial dynamics, volume pumping dynamics, and/or volume gravitational dynamics can be employed by the machine learning component 106 to model and/or simulate various fluid flow conditions associated with the one or more 3D models. In an aspect, the machine learning component 106 can also employ measured data and/or streamed data to set boundary conditions for one or more machine learning processes. For example, the machine learning component 106 can also employ measured data and/or streamed data to set boundary conditions for supply chambers and sink chambers and/or to establish driving forces for simulated physics phenomena (e.g., fluid dynamics, thermal dynamics, combustion dynamics, angular momentum, etc.).