Search

The transient electromagnetic method (TEM) is a geophysical exploration method that can efficiently acquire subsurface electrical parameters. For airborne, towed and other mobile platforms, TEM systems, large data volumes and the traditional one-dimensional denoising method with low efficiency and low signal-to-noise ratio (SNR) of late-time are the main bottlenecks limiting its reliable application. To address this problem, this paper proposes a neural network structure suitable for two-dimensional (2D) TEM data processing. The proposed structure combines a classical convolutional neural network denoising autoencoder with a gated recurrent neural network autoencoder, called the CNN-GRU dual autoencoder (CG-DAE). This method can directly input 2D TEM response data as images into the network for processing, which greatly improves data processing efficiency compared to single-time-channel processing. The simulation experiments verified the effectiveness of CG-DAE. After using CG-DAE denoising, the SNR of late-time (0.2–1 ms) signals is improved to nearly 29 dB, the 2D anomaly layer position is clear and the relative error (RE) between the denoised data and the corresponding clean data is <1.41%, while the RE of the late-time signals can be reduced to 3.68%. The proposed method can lay the foundation for fast processing of TEM data based on mobile platforms such as those that are airborne and/or towed. [ABSTRACT FROM AUTHOR]

In the semi-aviation frequency-domain electromagnetic measurement, the induction air-core coil and the differential pre-amplifier circuit introduce noise, which affects the sensor and results in receiving weak signals and improving the signal-to-noise ratio of the system. In response to this problem, by analyzing the physical structure of the air-core coil sensor and the mechanism of the amplification circuit, combined with the simulation and experimental tests of voltage noise, current noise, resistance noise and other noise components, analyzed that the thermal noise is the main component of the sensor noise in the system frequency band, but directly removing the matching resistor increases the instability of the circuit, causes the coil to work in an underdamped state, and generates a time domain oscillation at the resonant frequency, source impedance analysis and analysis of differential pre-amplifier circuit in the frequency-domain detection method, abandoning the matching resistance scheme and magnetic flux negative feedback scheme. The matching capacitor is added to make the receiver detect the frequency range in the 1–10 kHz range. In normal operation, the noise level reaches 10 nV level, which not only increases the stability of the circuit, but also reduces the noise of the sensor. It has far-reaching significance for the detection of weak frequency signals. [ABSTRACT FROM AUTHOR]