| dc.description.abstract | In current seismic acquisition practice, there is an increasing drive for data to be acquired sparsely in space, and often in irregular geometry. These surveys can trade off subsurface information for efficiency/cost - creating a problem of “missing seismic data” that can greatly hinder subsequent seismic processing and interpretation. Reconstruction of regularly sampled dense data from highly-sparse, irregular data can therefore aid in processing and interpretation of these far sparser, more efficient seismic surveys. Here, we compare two methods to solve the reconstruction problem in both space-time and wavenumber-frequency domain. Both of these methods require an operator that maps sparse to dense data: this operator is generally unknown, being the inverse of a known data sampling operator. As such, here our deterministic inversion is efficiently solved by least squares optimisation using an numerically-efficient Python-based linear operator representation. An alternative
method is the probabilistic approach that uses deep learning. Here, two specific deep learning architectures are benchmarked against each other and the deterministic approach; a Recurrent Inference Machine (RIM), which is designed specifically to solve inverse problems given known forward operators and the U-Net, originally designed for image segmentation tasks. The trained deep learning networks are capable of successfully mapping sparse to dense seismic data for a range of different datasets and decimation percentages, thereby significantly reducing spatial aliasing in the wavenumber-frequency domain. The deterministic inversion on the contrary, could not reconstruct the missing data in space-time domain and thus did not reduce the undesired spatial aliasing. Our results show that the application of Deep Learning for the seismic reconstruction is promising, but the treatment of large volume, multi-component seismic datasets will require dedicated learning architectures not yet realisable with existing tools. | |
