Determination of the Parameters of a Submerged Source by Perturbations of the Liquid Surface Based on Machine Learning Methods

The inverse problem of generating surface waves in a liquid is to determine the parameters of the source of perturbations from the waves it creates on the liquid surface. A new approach to solving this problem based on machine learning methods and the theory of neural networks is proposed. On the basis of the data from a laboratory experiment on water surface perturbations, the parameters of the model moving in the water column are restored.