High-Quality Signal Denoising and Deep Feature Representation and Its Application to the ENPEMF

Abstract

The Earth’s natural pulsed electromagnetic field (ENPEMF) signal is released by the instantaneous disturbance of the Earth’s naturally varying magnetic field, contains a large amount of information about the changing geological structures and their kinetic principles. The ENPEMF signals acquired by the equipment are often accompanied by a great deal of noise, and effective noise reduction is required for accurate signal analysis. We propose a new noise reduction method for a very low signal-to-noise ratio (SNR), called the Blaschke unwinding adaptive Fourier decomposition, and use synthetic signals to demonstrate the high accuracy of the proposed noise reduction method. Meanwhile, the Root-phase deep feature representation (RPDP) of the ENPEMF signal acquired during the Lushan Ms7.0 earthquake is explored using the roots obtained by Blaschke unwinding. The results show that the time-based RPDP can accurately reveal the deep feature of the ENPEMF signal before and after the earthquake, and extract the anomalous changes, potentially revealing the electromagnetic anomaly information contained in the ENPEMF signal.