Seismic super-resolution inversion method based on model-driven deep learning

Abstract

The invention discloses a seismic super-resolution inversion method based on model-driven deep learning, comprising the following steps: 1) mapping each iteration in the model-driven alternating direction multiplier method ADMM to each layer in the deep network, And use the mathematics-driven method to learn the proximal mapping, complete the construction of the deep network ADMM-SRINet; 2) obtain the label data used to train the deep network ADMM-SRINet; 3) use the obtained label data to perform Training; 4) Inverting the data to be tested using the deep network ADMM-SRINet trained in step 3). This method combines the advantages of the model-driven optimization method and the data-driven deep learning method to make the network structure interpretable; at the same time, due to the increase of physical knowledge, the iterative deep learning method alleviates the requirements for the training set, making The inversion results are more credible.

Description

Technical field [0001] The present invention belongs to the field of signal processing geophysical exploration involves inversion super-resolution seismic data, in particular a deep learning model-driven super-resolution seismic inversion method. Background technique [0002] In seismic exploration, as more and more complex research objectives, a clear depiction of the geological structure, lithology changes, fluid properties and other characteristics of the proposed exploration higher accuracy requirements. In recent years, seismic acquisition technology breakthrough has been made, in order to obtain a super-resolution (also known as high-resolution) seismic profiles laid the foundation, but still need to apply some processing techniques to pursue higher resolution. In order to improve the vertical resolution of seismic data, many techniques have been developed, such as a full band or band-limited deconvolution and inverse Q filtering. All of these methods can be implemented by ...

AI Technical Summary

Problems solved by technology

Due to the complexity of the surface and the low signal-to-noise ratio of seismic data, the current inversion resolution and fidelity are far from meeting the actual needs of oil and gas exploration and development.

Images