Multi-dimensional aerodynamic database development has become more and more impor- tant for the design, control and guidance of modern aircrafts. In order to relieve the curse of the dimensionality, we propose a novel flow field reconstruction method based on artificial neural network. The idea is to design a simplified problem which is related to the target problem. Then the map from the simplified problem to the target problem is built using an artificial neural network. Finally, the target problem can be predicted efficiently through solving the simplified problem instead. Examples of the efficiency of this approach include two-dimensional viscous nozzle flows, the inviscid M6 wing flow, and a viscous hypersonic flow of a complex configuration to evaluate the performance of the proposed method. With artificial neural network of moderate complexity, the solution of the target problem can be generated with good accuracy. Among other observations, we find that shocks can be predicted well with sharp resolution.