Narrow Results

The Baribis Fault is an important active fault in West Java, Indonesia. This fault has recently attracted the attention of many parties since some fault segments pass through densely populated areas, raising the risk of shallow earthquakes. The long-offset resistivity tomography method was applied to image the active Baribis Faults. This method clearly showed the subsurface geometry, including the contact characteristics of the Baribis Fault near the subsurface. The long-offset resistivity tomography surveys were acquired using multi-electrodes and multi-nodes, and the data acquisition was wirelessly controlled via a WiFi connection. The pole–dipole resistivity tomography image shows a 35^∘ dip overhang structure of the Baribis thrust fault near the Jatigede area in Middle Eastern West Java, with a strike fault segment in a relative East–West direction. However, the other long-offset tomography images in northeastern West Java, near the Conggeang–Sumedang area, show the oblique thrust fault phenomena of the Baribis Fault with a strike in the Northeast–Southwest direction. The stress caused by the Cimandiri–Lembang regional strike–slip fault likely influences the dynamics of the Baribis Fault in the close area of Sumedang.

A sample set of stratigraphic structure model airborne transient electromagnetic responses is established, the sample label is attached by unsupervised learning clustering technology, and the multilayer perceptron deep learning network with supervised learning is used to complete multiclassification tasks. Then, the sample set is input into the network for training to establish the inversion from the input response data to the output formation model. Verification results show that the prediction results are consistent with the types of sample stratigraphic models, which proves that the inversion method designed in this paper is correct, and efficient inversion from the test data to the prediction model is realized.