Saudi Arabian Oil Company

Schlumberger Technology Corporation

Daniele Colombo

Howard Khan Schmidt

Jesus Manuel Felix Servin

Frode Hveding

Diego Rovetta

Federico Miorelli

Gary Wayne Mcneice

Gary W McNeice

Brett Bouldin

Ernesto Sandoval-Curiel

Apostolos Kontakis

Ernesto Sandoval Curiel

Ersan Turkoglu

Nestor H Cuevas

Ping Zhang

Jianhui Xu

Jiuping Chen

Weichang Li

Graham Hitchcock

Sakethraman Mahalingam

Michael Wilt

Michael Jervis

Timothy H Keho

Taqi Yousuf Alyousuf

Mauro Pezzoli

Michael Anthony Jervis

Brett W Bouldin

Timothy Keho

A method for a physics-driven deep learning-based inversion coupled to fluid flow simulators may include obtaining measured data for a subsurface region, obtaining prior subsurface data for the subsurface region, and obtaining a physics-driven standard regularized joint inversion for at least two model parameters. The method may further include obtaining a case-based deep learning inversion characterized by a contracting path and an expansive path. The method may further include forming the physics-driven deep learning inversion with the physics-driven standard regularized joint inversion, the case-based deep learning inversion, and a coupling operator based on a penalty function. The method may further include forming a feedback loop between the physics-driven standard regularized joint inversion and the case-based deep learning inversion for re-training the case-based deep learning inversion. The method may further include generating an inversion solution for reservoir monitoring.

Physics-driven deep learning inversion coupled to fluid flow simulators

A method may include obtaining various seismic traces for a geological region of interest. The method may further include determining an offset attribute and an azimuthal attribute. The method may further include determining, using the offset attribute and the azimuthal attribute, a virtual trace bin for the geological region of interest. The method may further include generating a virtual trace using a subset of the seismic traces and corresponding to the virtual trace bin. The method may further include generating a velocity model for the geological region of interest using a virtual shot gather including the virtual trace and various virtual traces. A respective virtual trace among the virtual traces may correspond to a respective virtual trace bin among various virtual trace bins. The method may further include generating a seismic image of the geological region of interest using the velocity model.

Method and system for seismic processing using virtual trace bins based on offset attributes and azimuthal attributes

This specification describes workflows for, but is not limited to, performing full waveform inversion (FWI) to build high resolution velocity models to improve the accuracy of seismic imaging of a subterranean formation. This specification describes processes to automatically edit and enhance S/N quality of seismic data (such as land seismic data) to prepare the datasets for FWI. The methods for automatic corrections and pre-processing include: automatic iterative surface-consistent residual statics calculation, automatic rejection of anomalous traces (such as dead traces), and the automatic correction of surface-consistent amplitude anomalies (such as by scalar or deconvolution approaches). The operations include automatic 'muting' of noise before first arrivals.

Automatic data enhancement for full waveform inversion in the midpoint-offset domain

Methods and systems for identifying near-surface heterogeneities in a subterranean formation using surface seismic arrays can include: recording raw seismic data using sensors at ground surface; applying a band bass filter to the raw seismic data using a central frequency; picking a phase arrival time for the filtered data; generating an initial starting phase velocity model for tomographic inversion from the raw seismic data; applying tomographic inversion to the filtered data to generate a dispersion map associated at the central frequency; repeating the applying a band bass filter, picking a phase arrival time, generating an initial starting velocity model, and applying tomographic inversion steps for each of a set of central frequencies; and generating a three-dimensional dispersion volume representing near-surface conditions in the subterranean formation by combining the dispersion maps.

Mapping near-surface heterogeneities in a subterranean formation

A variable-frequency light source is configured to emit a light beam and modulate a frequency of the light beam. A fiber optic cable is attached to the variable frequency light source. The fiber optic cable is configured to receive the light beam at an inlet and pass the light beam to an exit. Multiple optical detectors are attached to the fiber optic cable. Each of the optical detectors is configured to detect a specified frequency of light that is backscattered through the fiber optic cable. An actuation mechanism is attached to the fiber optic cable. The actuation mechanism is configured to deform the fiber optic cable in response to a stimulus.

Determining structural tomographic properties of a geologic formation

An exemplary dissolvable assembly is provided. The dissolvable assembly includes a skeleton made from a first material, and a body made from a second material, wherein the first material and the second material dissolve at different rates.

Engineered composite assembly with controllable dissolution

Methods for full waveform inversion (FWI) in the midpoint-offset domain include using a computer system to sort seismic traces into common midpoint-offset bins (XYO bins). For each XYO bin, a linear moveout correction is applied to a collection of seismic traces within the XYO bin. The collection of seismic traces is stacked to form a pilot trace. The computer system determines a surface-consistent residual static correction for each seismic trace. The computer system determines that the surface-consistent residual static correction for each seismic trace is less than a threshold. Responsive to the determining that the surface-consistent residual static correction is less than the threshold, the computer system stacks the collection of seismic traces to provide the pilot trace. The computer system groups the pilot traces for the XYO bins into a set of virtual shot gathers. The computer system performs one-dimensional FWI based on each virtual shot gather.

Full waveform inversion in the midpoint-offset domain

Seismic data from seismic exploration surveys are mapped into a hypercube of bins or voxels in a four-dimensional space (X, Y, Offset, and Azimuth) according to Common Mid-Point (or CMP) between source and receivers. The mapped data from individual voxels or bins is then analyzed by multimodal statistics. Robust estimates of first break picks are obtained from the analysis. The first break picks are then used to as seed inputs for autopicking iteration, which proceeds to convergence. Estimates of confidence levels in the data are provided for re-picking to reduce computer processing time in successive autopicking iterations. Analysis is provided of different seismic attributes such as azimuthal velocity variations indicative of anisotropy, positioning errors of sources/receivers, geometry errors, and three dimensional distribution of inversion residuals. Analysis is also performed of standard deviation of the travel time data useful for estimating data errors in the inversion covariance matrix.

Automatic quality control of seismic travel time

Naturally-occurring, electromagnetic signals generated by interaction of solar wind with earth's magnetosphere adjacent a borehole are measured by an electromagnetic sensor positioned adjacent the borehole in the hydrocarbon-bearing formation. Electromagnetic signals generated within the borehole are measured over a period of time by a borehole sensor positioned within the borehole. The electromagnetic signals change over the period of time due to variations in fluid distributions within the hydrocarbon-bearing formation. Electromagnetic changes to the electromagnetic signals generated within the borehole and to the passive, naturally-occurring electromagnetic signals over the period of time are determined by one or more processors. A computational model of the hydrocarbon-bearing formation is generated based in part on the electromagnetic changes.

Capacitive electromagnetic formation surveillance using passive source

A system and method of evaluating and correcting for the effects of a near-surface anomaly on surface-to-borehole (STB) measurement data in a geological halfspace includes transmitting electromagnetic radiation from an EM source located on a ground surface which is positioned over the near-surface anomaly, measuring EM fields at a plurality of remote EM receivers located on the surface at a far distance from the EM source, obtaining vertical STB measurement data downhole, determining an orientation and moment of a secondary source equivalent dipole associated with the near-surface anomaly excited by the radiation transmitted by the EM source based on measurements of the EM fields at the plurality of remote receivers, determining a correction factor for the secondary source equivalent dipole on the EM field measurements at the plurality of remote receivers, and removing the effects of the near surface anomaly on the vertical STB measurement data using the correction factor.

Method for removing the effect of near surface galvanic distortion in surface to borehole EM measurements

A surface-consistent refraction analysis automatically derives near surface corrections during seismic data processing. Residual time lags are evaluated in multiple CMP-offset-azimuth bins by similarity analysis with a pilot trace where a correlation window is centered at the refracted arrival. The similarity analysis may take the form of computerized cross-correlation, or other criteria such as semblance. The residuals are then used to build a system of linear equations that is simultaneously inverted for surface-consistent shot and receiver time shift corrections plus a possible subsurface residual term. The refraction analysis steps are completely automated and require a fraction of the time needed for conventional near surface analysis.

Selection of pick values for automated near surface analysis

Systems, methods, and devices for performing real-time detecting and spatially-positioning a waterfront in an oil-producing reservoirs are disclosed. An example method of predicting movement of a waterfront in a reservoir may include generating a plurality of electrical signals having different frequencies with a surface electric source; injecting currents corresponding to the plurality of generated signals into the earth near a well extending into the reservoir with a surface dipole; sensing a vertical component of an electric field generated by each of the injected currents at a location in the reservoir with a sensor; detecting a location of the waterfront within the reservoir based on the received vertical components of the electric fields; and analyzing the detected vertical components of the electric fields taken on at least two different points in time with machine learning to predict a rate of movement of the waterfront within the reservoir.

Growing community of inventors

Dhahran, Saudi Arabia

Daniele Colombo