Abstract This article investigates bypassing the inversion steps involved in a standard litho-type classification pipeline and performing directly from imaged seismic data. We consider set of deep learning methods that map data into classes, trained on two variants synthetic data: (i) one which we image using local Radon transform to obtain angle gathers, (ii) another start subsurface-offset ba...

In crosswell seismic experiments, seismic sources are red in one well, and the waveeelds generated are measured in another well. The goal of the crosswell seismology is to nd physical parameters, especially the velocities, of the rocks between the wells from these measurements. This amounts to the mathematical problem of solving a coeecient inverse problem of the multidimensional acoustic wave ...

Finite difference is a simple, fast and effective numerical method for seismic wave modeling, and has been widely used in forward waveform inversion and reverse time migration. However, intensive calculation of three-dimensional seismic forward modeling has been restricting the industrial application of 3D pre-stack reverse time migration and inversion. Aiming at this problem, in this paper, a ...

INTRODUCTION Problem of reservoir estimation. The optimal exploitation of hydrocarbon reservoirs requires the accurate estimation of the reservoir's characteristics. Placement of wells, injection of gas and water, and production rate of hydrocarbons depend on the correct assessment of the reservoir properties. Furthermore, the field's properties change over tim e as reservoir pore fluid is remo...

State-of-the-art seismic imaging techniques treat inversion tasks such as full-waveform (FWI) and least-squares reverse time migration (LSRTM) partial differential equation-constrained optimization problems. Due to the large-scale nature, gradient-based algorithms are preferred in practice update model iteratively. Higher-order methods converge fewer iterations but often require higher computat...

When redundancy of seismic data exists factorial cokriging enables the estimation of (1) a common part, based on the common spatial behavior, and (2) the differences relative to the common part of the input data. Coléou (2002) first introduced the automatic implementation of factorial co-kriging (AFACK) as a filtering technique for the time-lapse (4D) processing sequence. It was specifically de...

Much of the difficulties in characterizing complex reservoirs are related to the uncertainty associated with seismic interpretation. In this project, we examine two such sources: uncertainty in the velocity model, and ambiguities with expert interpretation due to conceptual geological uncertainty of reservoir structure. We address the first issue by presenting a geostatistical method for genera...

The LSQR algorithm developed by Paige and Saunders (1982) is considered one of the most efficient and stable methods for solving large, sparse, and ill-posed linear (or linearized) systems. In seismic tomography, the LSQR method has been widely used in solving linearized inversion problems. As the amount of seismic observations increase and tomographic techniques advance, the size of inversion ...