Multiscale transform based seismic reflectivity inversion using convolutional neural network

TL;DR

This paper introduces a multiscale Fourier transform method combined with convolutional neural networks for seismic reflectivity inversion, enabling wavelet-independent, sparse, and direct inversion on depth-migrated data, improving accuracy without prior models.

Contribution

It presents a novel multiscale Fourier transform approach integrated with CNNs for seismic inversion that does not require wavelet extraction or initial models, applicable directly to depth data.

Findings

Accurate reflectivity inversion without wavelet extraction.

Inversion results closely match well-log impedance.

Method effective on both synthetic and real seismic data.

Abstract

The Multiscale Fourier Transform of a seismic trace performs time-frequency analyses over a range of window lengths. The variation in window length captures local and global relative amplitudes between events, thereby allowing reflectivity inversion that is independent of the amplitude spectrum of the seismic wavelet. As the temporal and spatial variation of the actual seismic wavelet in seismic reflection data is poorly known, this approach has many advantages over conventional seismic reflectivity inversion. No wavelet extraction is performed. Thus, the inversion for reflectivity can be conducted without well control, seismic ties, or time-depth functions. The inversion is sparse, so no starting model is needed. Furthermore, as no wavelet is required, the inversion can be applied directly to depth migrated data. The phase of the wavelet is constrained by the assumption of sparse reflectivity and thus works best when earth impedance structure is blocky. Trace integration of the inverted reflectivity provides bandlimited impedance which compares very favorably to well-log bandlimited impedance for both synthetic and real data cases.