An ATEM 1D inversion based on K-Means clustering and MLP deep learning

Abstract Traditional geophysical inversion methods rely on an assumption of prior knowledge, starting from the establishment of the initial model and ending with the model being modified many times. This iterative process makes the forward modelling results move increasingly closer to the observed data. However, each inversion step requires multiple forward calculations, which consumes considerable time and computing resources. This is the greatest obstacle to real-time inversion at present. Airborne transient electromagnetic (ATEM) response data are collected in a time-channel manner. The different stratigraphic structures reveal different time-varying electromagnetic response laws. In this paper, deep learning technology is used to advance the ‘model correction-forward iteration’ step in the geophysical inversion process to the data preprocessing stage, to better adapt to the specialty of ATEM, improve the efficiency of the inversion and shorten the inversion time. In this method, a sample set composed of a ‘stratigraphic texture model—ATEM response’ is established, the K-Means clustering technique of unsupervised learning is used to complete the sample tag attachment, and the multilayer perceptron (MLP) deep learning network with supervised learning is used to complete the multiclassification tasks. Then, the sample sets are input into the deep learning network for training to build the inversion from the input response data to the output of the stratigraphic model. Finally, the inversion flow is verified with test set samples. The prediction results are consistent with the simulated data, and the inversion, from the test data to the prediction model, is implemented efficiently.