Resistivity-depth Imaging with the Airborne Transient Electromagnetic Method Based on an Artificial Neural Network

We developed an artificial neural network to map the distribution of geologic conductivity in the earth subsurface using the airborne transient electromagnetic method. The artificial neural network avoids the need for complex derivations of electromagnetic field formulas and requires only input and transfer functions to obtain a quasi-resistivity image. First, training sample set from the airborne transient electromagnetic response of homogeneous half-space models with different resistivities was formed, and net work model parameters, including the flight altitude, time constant, and response amplitude, were determined. Then, a double-hidden-layer back-propagation (BP) neural network was established based on the mapping relationship between quasi-resistivity and airborne transient electromagnetic response. By analyzing the mean square error curve, the training termination criterion of the BP neural network was determined. Next, the trained BP neural network was used to interpret the airborne transient electromagnetic responses of various typical layered geo-electric models, and the results were compared with that from the all-time apparent resistivity algorithm. The comparison indicated that the resistivity imaging from the BP neural network approach was much closer to the true resistivity of the model, and the response to anomalous bodies was better than that from an all-time apparent resistivity. Finally, this imaging technique was used to process field data acquired by employing the airborne transient method from the HuaYin survey area. Quasi-resistivity depth sections calculated with the BP neural network and the actual geological situation were in good.