Ground dragging type transient electromagnetic imaging method and system

The invention provides a ground dragging type transient electromagnetic imaging method and system, and belongs to the technical field of geophysical methods and artificial intelligence, and the method comprises the steps: inputting the collected actual observation transient electromagnetic response data of the ground into a trained CNN-LSTM network model, and obtaining a target resistivity model; the training process of the CNN-LSTM network comprises the following steps: obtaining theoretical observation transient electromagnetic response data through transient electromagnetic forward modeling by adopting a theoretical model; constructing a layered resistivity model by adopting B-spline interpolation, and constructing a data set label; and taking the data set label as an input, adding the accumulated sensitivity of the smooth constraint term and the resistivity into a loss function, and taking the resistivity predicted by the network as an output to train a CNN-LSTM network model. According to the invention,