Smooth Deep Learning Magnetotelluric Inversion Based on Physics-Informed Swin Transformer and Multiwindow Savitzky-Golay Filter

Despite exhibiting excellent inversion results for synthetic data in magnetotelluric (MT) inversion, applying deep learning (DL) to directly inverting MT field data remains challenging. In this study, different from most previous works that mainly focus on generating massive representative resistivity models to cover the solutions of the field data or constructing a strong network by employing advanced DL techniques, we provide a new perspective in that a multiwindow Savitzky-Golay (MWSG) filter is proposed to first smooth the apparent resistivity and phase derived from the MT field measurements before network prediction. This smoothing operation aims to promote the actual apparent resistivity and phase to be close in morphology and smoothness to the training input data, i.e., to adapt the field data to the training sample data. Then, the smoothed apparent resistivity and phase, instead of the original ones, are fed into the well-trained network for instantaneous inversion. Because we create a set of layered resistivity models with gradual-changing resistivity to act as desired output during network training, it together with the proposed MWSG filter enables this work to achieve smooth inversion. Besides, we introduce Swin Transformer (SwinT) to improve the efficiency of MT DL inversion, based on which a physics-informed SwinT (PISwinT) is implemented to enhance the generalization capability. We demonstrate the proposed PISwinT-MWSG smooth inversion method in both synthetic and field MT cases, and it is expected to improve the adaptability and practicability of the DL method to directly solve the inverse problems in MT surveys.

Automated summary

Despite the challenges in directly inverting MT field data using deep learning, this study proposes a new method that applies a multiwindow Savitzky-Golay filter to smooth the MT field measurements before network prediction. The smoothed data is then fed into a trained network for inversion. The use of layered resistivity models and the proposed MWSG filter enables smooth inversion. The efficiency of MT DL inversion is improved by incorporating Swin Transformer, and a physics-informed version is implemented to enhance generalization capability. The proposed method is demonstrated in both synthetic and field MT cases, showing improved adaptability and practicability for inverse problems in MT surveys.