The velocity, attitude and altitude of flight vehicles have typically been measured with booms that extend from the vehicle surface out into the flow field. However, this arrangement was found to be unacceptable for certain flight applications. Instrumentation was therefore developed by other researchers to measure the flight parameters using an array of pressure measurements located on the surface of the vehicle. The relationship between these pressure measurements and the air data is a complex non-linear function that is not easily described with simple aerodynamic models. The focus of this work was to analyze this system, and develop modeling techniques to describe the functionality between measured and estimated parameters. This system was characterized using both fluid dynamics and novel data processing techniques, and the system was subsequently modeled using a combination of physical and neural network models. Statistical techniques were also developed to identify and isolate lost input signals. The resulting systems of models were shown to be accurate and robust to noise in the input signals. Additionally, the neural network models were shown to be stable across the entire relevant range of new input data, including both interpolation within and extrapolation outside the original domain of the training data. Finally, back-propagation neural networks were shown to be well suited to this air data measurement technique. The networks were shown to work well with the available vehicle geometry, and were found to be scalable to other vehicle shapes.