Proper orthogonal decomposition and physical field reconstruction with artificial neural networks (ANN) for supercritical flow problems

•A hybrid RBF-MLP model was tested to achieve a highly nonlinear approximation.•A POD technique was employed to define a low-dimensional reduced-order system.•A POD-ANN model was developed to accurately reconstruct the principal flow features.•The combination of POD and machine learning can reveal the underlying physical mechanisms of flow features.