Method, system and equipment for converting magnetic field data by inducing electromotive force through transient electromagnetic method
By constructing a residual deep learning model and utilizing one-dimensional convolutional residual blocks, bidirectional long short-term memory networks, and multi-head self-attention mechanisms, an efficient conversion of induced electromotive force to magnetic field data was achieved. This solved the problem that transient electromagnetic instruments could not convert magnetic field data and improved the ability to mine deep geoelectric structure information.
CN118897327AActive Publication Date: 2024-11-05CHINA UNIV OF GEOSCIENCES (WUHAN)
Patent Information
- Application Number
- CN202410998826.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-24
Smart Images

Figure CN118897327A_ABST
Abstract
The invention discloses a method and system for converting induced electromotive force into magnetic field data through a transient electromagnetic method, a storage medium and computer equipment, and relates to the field of geophysical exploration, and the method for converting induced electromotive force into magnetic field data through the transient electromagnetic method mainly comprises the steps: constructing an induced electromotive force and magnetic field data set of the transient electromagnetic method; loading full-waveform response to the generated lower step induced electromotive force data; building a deep learning model based on a residual attention mechanism; training the model and performing parameter tuning based on Bayesian optimization; and converting the induced electromotive force by using the trained model to obtain magnetic field data. According to the method and system for converting the magnetic field data through the transient electromagnetic method induced electromotive force, the storage medium and the computer equipment, the accuracy and efficiency of magnetic field data conversion can be improved, and deep geoelectric structure information contained in existing mass induced electromotive force data can be effectively mined.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Intelligent building non-intrusive load decomposition method based on parallel connection network
CN115392318A
Sensitive information classification method and device based on multi-modal attention fusion
CN117235605A
Transient electromagnetic scanning detection system and method
CN117590476A
Adjacent well detection apparatus, method and system
US20230393296A1
