The present disclosure describes methods and systems, including computer-implemented methods, computer program products, and computer systems, for suppressing noises in seismic data. One computer-implemented method includes receiving, at a data processing apparatus, a set of seismic data associated with a subsurface region; flattening, by the data processing apparatus, the set of seismic data according to an identified seismic event; dividing, by the data processing apparatus, the set of seismic data into a plurality of spatial windows; randomizing, by the data processing apparatus, the set of seismic data according to a random sequential order; filtering, by the data processing apparatus, the randomized seismic data; and reorganizing, by the data processing apparatus, the filtered seismic data according to a pre-randomization order.

A method to generate a vertical seismic profile includes acquiring a set of distributed acoustic sensing measurements from a set of overlapping measurement channels on an optical fiber, wherein each of the set of distributed acoustic sensing measurements are measured at a gauge length. The method also includes generating a set of virtual seismic measurements corresponding with subdivisions in the set of overlapping measurement channels based on the set of distributed acoustic sensing measurements and generating the vertical seismic profile based on the set of virtual seismic measurements.

Estimating an earth response can include deconvolving a multi-dimensional source wavefield from near-continuously recorded seismic data recorded at a receiver position. The deconvolving can include spreading the near-continuously recorded seismic data across a plurality of possible source emission angles. The result of the deconvolution can be the earth response estimate.

Hydrocarbon exploration and extraction can be facilitated using machine-learning models. For example, a system described herein can receive seismic data indicating locations of geological bodies in a target area of a subterranean formation. The system can provide the seismic data as input to a trained machine-learning model for determining whether the target area of the subterranean formation includes one or more types of geological bodies. The system can receive an output from the trained machine-learning model indicating whether or not the target area of the subterranean formation includes the one or more types of geological bodies. The system can then execute one or more processing operations for facilitating hydrocarbon exploration or extraction based on the seismic data and the output from the trained machine-learning model.

A method of enhancing seismic images includes receiving a seismic gather. The seismic gather includes a plurality of seismic traces. A feature trace is generated based on the plurality of seismic traces in the seismic gather. For each of the plurality of seismic traces in the seismic gather, a correlation trace is generated based on that seismic trace and the feature trace, the correlation trace is modified using an activation function, and an enhanced trace is generated by multiplying that seismic trace with the modified correlation trace.

Implementations described and claimed herein provide systems and methods for isolation detection. In one implementation, an acoustic signal is obtained. The acoustic signal is captured at a set of acoustic receivers deployed in a structure in a subterranean surface. A differential acoustic signal is produced from the acoustic signal captured at the set of acoustic receivers. A symmetry within a portion of the structure is determined based on a value of the differential acoustic signal. At least one isolation region is detected within the structure based on the symmetry.

Implementations described and claimed herein provide systems and methods for isolation detection. In one implementation, an axial acoustic signal is obtained. The axial acoustic signal is captured using an axial sensor deployed in a structure in a subterranean surface. The axial acoustic signal is separated into a first wave region and a second wave region by applying velocity filtering. An axial symmetry of a portion of the structure is determined based on at least one of the first wave region or the second wave region.

Implementations described and claimed herein provide systems and methods for isolation detection. In one implementation, a radial acoustic log is obtained. The radial acoustic log is captured using a radial sensor of an acoustic logging tool deployed within a first structure. The first structure disposed within a second structure in a subterranean environment. A radial symmetry is determined using the radial acoustic log. An eccentricity of the first structure relative to the second structure is determined based on the radial symmetry.

A method to generate a vertical seismic profile includes acquiring a set of distributed acoustic sensing measurements from a set of overlapping measurement channels on an optical fiber, wherein each of the set of distributed acoustic sensing measurements are measured at a gauge length. The method also includes generating a set of virtual seismic measurements corresponding with subdivisions in the set of overlapping measurement channels based on the set of distributed acoustic sensing measurements and generating the vertical seismic profile based on the set of virtual seismic measurements.

Various implementations directed to quality control and preconditioning of seismic data are provided. In one implementation, a method may include receiving particle motion data from particle motion sensors disposed on seismic streamers. The method may also include performing quality control (QC) processing on the particle motion data. The method may further include performing preconditioning processing on the QC-processed particle motion data. The method may additionally include attenuating noise in the preconditioning-processed particle motion data.