Noise suppression for magnetotelluric sounding data based on signal subspace enhancement and endpoint detection

Abstract

To retain useful information of magnetotelluric low frequency band and improve the capacity of magnetotelluric deep detection in ore concentration area with complex noises, the combined signal subspace enhancement with endpoint detection is proposed based on morphology filtering to secondary signal-to-noise separation processing. Firstly, aimed at noise contour extracted by morphology filtering, we use signal subspace enhancement to separate signal subspace and noise subspace for pretreatment. Secondly, the signal subspace is combined with reconstructed signal and the noise subspace is set to zero. Finally, endpoint detection for post-processing is carried out in order to identify the start and end points of the waveform mutation. Simulated results show that Cagniard resistivity curve in the low frequency band has been improved obviously, and the apparent resistivity value is relatively stable. The proposed method is better to offset the loss of low frequency useful information in the process of the morphological filtering, and the results can even more truly reflect the inherent deep structural information of low frequency components for the measured point itself.