Abstract: Systems and methods for reservoir modeling include a super resolution seismic data conversion platform for converting input seismic data into high resolution output seismic data. The super resolution seismic data conversion platform can perform a super resolution inversion on the input seismic data by imposing sparsity and/or coherency assumptions on geophysical parameters represented by wavelet information of the input seismic data. For instance, a seismic trace interval can be determined, and both a reflection coefficient and an acoustic impedance of the seismic trace interval can be constrained. An optimization problem, using the constrained reflection coefficient and the constrained acoustic impedance, can be generated and/or solved by a sparse inversion. As such, a vertical resolution, as well as a seismic bandwidth, of super resolution output seismic data can be increased, improving subterranean feature (e.g., sand and/or shale characteristics) interpretation and well planning and construction.

Abstract: Method for acquiring seismic data is described. The method includes determining a non-uniform optimal sampling design that includes a compressive sensing sampling grid. Placing a plurality of source lines or receiver lines at a non-uniform optimal line interval. Placing a plurality of receivers or nodes at a non-uniform optimal receiver interval. Towing a plurality of streamers attached to a vessel, wherein the plurality of streamers is spaced apart at non-uniform optimal intervals based on the compressive sensing sampling grid. Firing a plurality of shots from one or more seismic sources at non-uniform optimal shot intervals. Acquiring seismic data via the plurality of receivers or nodes.

Abstract: A method for 2D seismic data acquisition includes determining source-point seismic survey positions for a combined deep profile seismic data acquisition with a shallow profile seismic data acquisition wherein the source-point positions are based on non-uniform optimal sampling. A seismic data set is acquired with a first set of air-guns optimized for a deep-data seismic profile and the data set is acquired with a second set of air-guns optimized for a shallow-data seismic profile. The data are de-blended to obtain a deep 2D seismic dataset and a shallow 2D seismic dataset.

Abstract: A multi-stage inversion method for deblending seismic data includes: a) acquiring blended seismic data from a plurality of seismic sources; b) constructing an optimization model that includes the acquired blended seismic data and unblended seismic data; c) performing sparse inversion, via a computer processor, on the optimization model; d) estimating high-amplitude coherent energy from result of the performing sparse inversion in c); e) re-blending the estimated high-amplitude coherent energy; and f) computing blended data with an attenuated direct arrival energy.

Abstract: The present invention discloses systems and methods for attenuation of coherent environmental and source-generated noise in a continuously recorded domain of seismic survey testing. Rather than applying universal de-noising techniques to conventional gathers after source de-blending, the system and methods discussed herein focus on estimating and removing noise directly on continuous records by leveraging the noise characteristics in the domain of natural recording. Such techniques may equally be applied to coherent environmental and source-generated noises on seismic data as well as other data and noise types. Driven by the noise types encountered in the field, the methods of noise attenuation may be based upon time-frequency domain rank reduction techniques. Further, to model signal and/or noise, low-rank approximations are employed in conjunction with other techniques such as operator design and unsupervised learning.

Abstract: Various aspects described herein relate to a machine learning based signal recovery. In one example, a computer-implemented method of noise contaminated signal recovery includes receiving, at a server, a first signal including a first portion and a second portion, the first portion indicative of data collected by a plurality of sensors, the second portion representing noise; performing a first denoising process on the first signal to filter out the noise to yield a first denoised signal; applying a machine learning model to determine a residual signal indicative of a difference between the first signal and the first denoised signal; and determining a second signal by adding the residual signal to the first denoised signal, the second signal comprising (i) signals of the first portion with higher magnitudes than the noise in the second portion, and (ii) signals of the first portion having lower magnitudes than the noise in the second portion.

Abstract: Method for acquiring seismic data is described. The method includes determining a non-uniform optimal sampling design that includes a compressive sensing sampling grid. Placing a plurality of source lines or receiver lines at a non-uniform optimal line interval. Placing a plurality of receivers or nodes at a non-uniform optimal receiver interval. Towing a plurality of streamers attached to a vessel, wherein the plurality of streamers is spaced apart at non-uniform optimal intervals based on the compressive sensing sampling grid. Firing a plurality of shots from one or more seismic sources at non-uniform optimal shot intervals. Acquiring seismic data via the plurality of receivers or nodes.

Abstract: Method for acquiring seismic data is described. The method includes determining a non-uniform optimal sampling design that includes a compressive sensing sampling grid. Placing a plurality of source lines or receiver lines at a non-uniform optimal line interval. Placing a plurality of receivers or nodes at a non-uniform optimal receiver interval. Towing a plurality of streamers attached to a vessel, wherein the plurality of streamers is spaced apart at non-uniform optimal intervals based on the compressive sensing sampling grid. Firing a plurality of shots from one or more seismic sources at non-uniform optimal shot intervals. Acquiring seismic data via the plurality of receivers or nodes.

Abstract: Leveraging migration and demigration, here we propose a learning-based approach for fast denoising with applications to fast-track processing. The method is designed to directly work on raw data without separating each noise type and character. The automatic attenuation of noise is attained by performing migration/demigration guided sparse inversion. By discussing examples from a Permian Basin dataset with very challenging noise issues, we attest the feasibility of this learning-based approach as a fast turnaround alternative to conventional denoising methodology.

Abstract: A multi-stage inversion method for deblending seismic data includes: a) acquiring blended seismic data from a plurality of seismic sources; b) constructing an optimization model that includes the acquired blended seismic data and unblended seismic data; c) performing sparse inversion, via a computer processor, on the optimization model; d) estimating high-amplitude coherent energy from result of the performing sparse inversion in c); e) re-blending the estimated high-amplitude coherent energy; and f) computing blended data with an attenuated direct arrival energy.

Abstract: A multi-stage inversion method for deblending seismic data includes: a) acquiring blended seismic data from a plurality of seismic sources; b) constructing an optimization model that includes the acquired blended seismic data and unblended seismic data; c) performing sparse inversion, via a computer processor, on the optimization model; d) estimating high-amplitude coherent energy from result of the performing sparse inversion in c); e) re-blending the estimated high-amplitude coherent energy; and f) computing blended data with an attenuated direct arrival energy.

Abstract: A method for 2D seismic data acquisition includes determining source-point seismic survey positions for a combined deep profile seismic data acquisition with a shallow profile seismic data acquisition wherein the source-point positions are based on non-uniform optimal sampling. A seismic data set is acquired with a first set of air-guns optimized for a deep-data seismic profile and the data set is acquired with a second set of air-guns optimized for a shallow-data seismic profile. The data are de-blended to obtain a deep 2D seismic dataset and a shallow 2D seismic dataset.

Abstract: A method for 2D seismic data acquisition includes determining source-point seismic survey positions for a combined deep profile seismic data acquisition with a shallow profile seismic data acquisition wherein the source-point positions are based on non-uniform optimal sampling. A seismic data set is acquired with a first set of air-guns optimized for a deep-data seismic profile and the data set is acquired with a second set of air-guns optimized for a shallow-data seismic profile. The data are de-blended to obtain a deep 2D seismic dataset and a shallow 2D seismic dataset.

Abstract: Method for acquiring seismic data is described. The method includes determining a non-uniform optimal sampling design that includes a compressive sensing sampling grid. Placing a plurality of source lines or receiver lines at a non-uniform optimal line interval. Placing a plurality of receivers or nodes at a non-uniform optimal receiver interval. Towing a plurality of streamers attached to a vessel, wherein the plurality of streamers is spaced apart at non-uniform optimal intervals based on the compressive sensing sampling grid. Firing a plurality of shots from one or more seismic sources at non-uniform optimal shot intervals. Acquiring seismic data via the plurality of receivers or nodes.

Abstract: Method for acquiring seismic data is described. The method includes determining a non-uniform optimal sampling design that includes a compressive sensing sampling grid. Placing a plurality of source lines or receiver lines at a non-uniform optimal line interval. Placing a plurality of receivers or nodes at a non-uniform optimal receiver interval. Towing a plurality of streamers attached to a vessel, wherein the plurality of streamers is spaced apart at non-uniform optimal intervals based on the compressive sensing sampling grid. Firing a plurality of shots from one or more seismic sources at non-uniform optimal shot intervals. Acquiring seismic data via the plurality of receivers or nodes.

Abstract: A multi-stage inversion method for deblending seismic data includes: a) acquiring blended seismic data from a plurality of seismic sources; b) constructing an optimization model that includes the acquired blended seismic data and unblended seismic data; c) performing sparse inversion, via a computer processor, on the optimization model; d) estimating high-amplitude coherent energy from result of the performing sparse inversion in c); e) re-blending the estimated high-amplitude coherent energy; and f) computing blended data with an attenuated direct arrival energy.

Abstract: A method for 2D seismic data acquisition includes determining source-point seismic survey positions for a combined deep profile seismic data acquisition with a shallow profile seismic data acquisition wherein the source-point positions are based on non-uniform optimal sampling. A seismic data set is acquired with a first set of air-guns optimized for a deep-data seismic profile and the data set is acquired with a second set of air-guns optimized for a shallow-data seismic profile. The data are de-blended to obtain a deep 2D seismic dataset and a shallow 2D seismic dataset.

Abstract: Various aspects described herein relate to a machine learning based signal recovery. In one example, a computer-implemented method of noise contaminated signal recovery includes receiving, at a server, a first signal including a first portion and a second portion, the first portion indicative of data collected by a plurality of sensors, the second portion representing noise; performing a first denoising process on the first signal to filter out the noise to yield a first denoised signal; applying a machine learning model to determine a residual signal indicative of a difference between the first signal and the first denoised signal; and determining a second signal by adding the residual signal to the first denoised signal, the second signal comprising (i) signals of the first portion with higher magnitudes than the noise in the second portion, and (ii) signals of the first portion having lower magnitudes than the noise in the second portion.

Abstract: A multi-stage inversion method for deblending seismic data includes: a) acquiring blended seismic data from a plurality of seismic sources; b) constructing an optimization model that includes the acquired blended seismic data and unblended seismic data; c) performing sparse inversion, via a computer processor, on the optimization model; d) estimating high-amplitude coherent energy from result of the performing sparse inversion in c); e) re-blending the estimated high-amplitude coherent energy; and f) computing blended data with an attenuated direct arrival energy.