The transient electromagnetic method employed in aeromagnetic surveys has been widely used for geophysical, petroleum, and engineering exploration because geophysical characteristics can be predicted as an inversion problem based on measured electromagnetic response data. However, this process requires uniformly and densely distributed electromagnetic response data, which are typically unavailable in actual TEM applications due to the high cost of the aeromagnetic surveys, which necessitates the use of large grid patterns to effectively map large areas. Therefore, developing methods for predicting missing electromagnetic response data based on the available data is essential for ensuring the accurate characterization of geological bodies. The present work addresses this issue by establishing an electromagnetic response curve prediction model based on a temporal convolutional network (TCN) architecture. Firstly, the electromagnetic response data is subjected to grey relational analysis to obtain correlations and reduce the data dimension. Secondly, the response data with correlation degrees greater than a threshold are selected as TCN model input. Finally, the TCN model establishes the nonlinear relationship between the electromagnetic response parameter sequence and its output sequence. The proposed model and other existing state-of-the-art prediction models are applied to actual electromagnetic prospecting data, and the results demonstrate that the proposed TCN model provides higher prediction accuracy and stronger robustness than the other models considered. Moreover, the proposed model is suitable for processing multiple series of related data, such as electromagnetic response prediction models. Therefore, the proposed model has good application prospects in electromagnetic response prediction and electromagnetic response recovery research.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Geologic evolution of the Tibetan plateau is characterized by crustal extension and horizontal movement in the post-collision stage, during which, approximate north–south (N–S) trending tectonic belts typically represented by Tangra-Yumco rift are developed. The Tangra-Yumco tectonic belt is an ideal object to investigate the deep structure and mechanism of the crustal extension. The magnetotelluric (MT) method is effective in probing crustal structures, especially for high-conductivity bodies. A MT profile of east–west direction with dense stations has been carried out across the Tangra-Yumco tectonic belt. Resistivity models independently derived from two-dimensional and three-dimensional inversions provided more detailed geophysical constraints on the mechanism of crustal extension and deformation. A significant conductor with estimated melt fraction as 3.0–7.5% in mid-lower crust was revealed under the N–S tectonic belt, where the asthenospheric upwelling through the slab-tearing window might have induced partial melting of the lithospheric mantle and lower crust. Combined with previous studies, the upward migration of hot mantle materials and the expansion of the lower crust should be the primary mechanism driving east–west (E–W) extension of the brittle upper crust with high resistivity above the depth of 30 km. According to lateral electrical discontinuity in the upper crust, we inferred that there might exist three normal faults with the reference of topography and the trend of extension of the existing faults. The expansion and deformation of the conductor might have pulled the brittle upper crust and cause significant E–W extension, leading to the formation of the approximate N–S trending rift and normal faults.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.