公开(公告)号：US10809412B2

公开(公告)日：2020-10-20

申请号：US15851754

申请日：2017-12-22

申请人： Institute of Geology and Geophysics, Chinese Academy of Sciences

发明人： Qingyun Di ,  Guoqiang Xue ,  Ruo Wang ,  Zhiguo An ,  Changmin Fu ,  Da Lei ,  Xianjun Zhuo ,  Zhongxing Wang

IPC分类号： G01V3/12 ,  G01V3/38

摘要： A WEM-based method for deep resource detection using sky waves refers to the technical field of deep resource detection. The proposed method of deep detection using sky waves improves the traditional “atmospheric-lithosphere” half-space propagation theory into a full-space “sky wave” theory of “ionosphere-atmosphere-rock layer”, that is, the influence of the ionosphere and the displacement current in the air are taken into consideration to obtain a new precise expression of “sky wave” response, which is suitable for full space, slow attenuation and long distance propagation. A receiving device for sky wave signal has been developed. Through theoretical model calculation and actual data measurement, it is known that it is possible to use the sky wave for detection within the scope of China's national territory to realize the high-precision electrical structural exploration within a depth of 10 kilometers and open a new era of artificial source electromagnetic detection.

公开(公告)号：US11782183B2

公开(公告)日：2023-10-10

申请号：US17840458

申请日：2022-06-14

申请人： Institute of Geology and Geophysics, Chinese Academy of Sciences

发明人： Zhongxing Wang ,  Lili Kang ,  Zhiguo An ,  Ruo Wang ,  Xiong Yin

IPC分类号： G01V3/08 ,  G01V99/00 ,  G06N3/08

CPC分类号： G01V99/005 ,  G01V3/087 ,  G01V3/088 ,  G06N3/08

摘要： Disclosed is a magnetotelluric inversion method based on a fully convolutional neural network. The magnetotelluric inversion method includes: constructing a multi-dimensional geoelectric model; constructing a fully convolutional neural network structure model to obtain initialized fully convolutional neural network model parameters; training and testing the fully convolutional neural network structure model based on the training sets and the test sets to obtain optimized fully convolutional neural network structure model parameters; determining whether training of the fully convolutional neural network structure model is completed according to fitting error changes corresponding to the training sets and the test sets; and finally, inputting measured apparent resistivity into a trained fully convolutional neural network structure model for inversion, and further optimizing the fully convolutional neural network structure model by analyzing precision of an inversion result until an inversion fitting error satisfies a set error requirement.