Conductivity Depth Imaging of Helicopter-borne TEM data using Artificial Neural Network based on pseudo-layer model

摘要：

Conductivity depth imaging is commonly used in practical survey and further it also provides the start model for inversion. We developed an artificial neural network approach for CDI of Helicopter-borne time-domain electromagnetic data based on pseudo-layer model. This ANN approach is not only immunity to altimeter errors but also gets better resolutions for both resistive and conductive detecting and for thin layer distinguishing than lookup table method. We used the forward modeling as the training data set and test data set. Logarithmic normalization and linear normalization are used for the input and output. The results of Huangs two synthetic models indicate the ANN pseudo-layer half space approach is a fast and effective algorithm for CDI of HTEM data.

关键词： Artificial neural network Conductivity depth imaging Helicopter-borne time-domain electromagneticmethod Pseudo-layer half space model

作者: ZHU Kaiguang LIN Jun HAN Yuehui ZHOU Fengdao

作者单位: Key laboratory of Geo-exploration instrumentation, College of Instrumentation and electrical engineering, Changchun, Jilin University

会议类型: 国际会议

会议名称: The 19th International Workshop on Electromagnetic Induction in the Earth(第十九届国际地球电磁感应学术研讨会)

会议地点: 北京

会议语种:英文

页码: 589-592

在线出版日期: 2008-10-23（万方平台首次上网日期，不代表论文的发表时间）