A machine-implemented method, at least one non-transitory computer-readable medium storing instructions, and a computing system are provided for attenuating noise. A computing system receives a seismic image and generates a first image using a first neural network configured to identify low-frequency ground roll in a seismic image, and a second image using a second neural network configured to identify reflections in the seismic image. A combined image is generated by combining the first image and the second image. The first neural network and the second neural network are adjusted to reduce a difference between the combined image and the seismic image using frequency constraint to guide separation of the seismic image into the first image and the second image.

A method for performing a formation-related operation based on corrected vertical seismic profile (VSP) data of an earth formation includes performing a VSP survey and applying a normal moveout (NMO) correction equation to the survey data that is a function of source offset to wellhead. The method also includes solving the NMO correction equation using a simulated annealing algorithm having an object function that is a coherence coefficient of semblance analysis of an NMO corrected reflection event within a time window to provide NMO corrected data. The method further includes performing the formation-related operation at at least one of a location, a depth and a depth interval based on the VSP NMO corrected data.

A system for seismic imaging of a subterranean geological formation, the system includes a receiver configured to obtain seismic data comprising a data volume representing a post-stacked image. The system includes a filtering module configured to: apply frequency-wavenumber (F-K) filter to the data volume extract a negative-dip structure image and apply the frequency-wavenumber (F-K) filter to the data volume extract a positive-dip structure image. The system includes a diffraction rendering module configured to: multiply the positive-dip structure image with the negative-dip structure image and generate a diffraction-enhanced seismic image representing a geological formation of the data volume.

Seismic exploration methods and data processing apparatuses employ a deep neural network to remove seismic interference (SI) noise. Training data is generated by combining an SI model extracted using a conventional model from a subset of the seismic data, with SI free shots and simulated random noise. The trained DNN is used to process the entire seismic data thereby generating an image of subsurface formation for detecting presence and/or location of sought-after natural resources.

An apparatus includes a signal acquisition part acquires oscillation signals from sensors provided under lanes of a bridge and close to an expansion joint, a signal separation part applies BSS to the oscillation signals to estimate source oscillation signals respectively separated in the plurality of lanes, and adjusts amplitude of the source oscillation signals to output amplitude adjusted oscillation signals, and a vehicle estimation part estimates, from the amplitude adjusted oscillation signal, a response oscillation due to a vehicle passing on the lane of interest to detect and count vehicles passing on the lane.

An optical communication system that enables any deployed fiber-optic cable to function as an earthquake-detection sensor. In an example embodiment, a WDM optical transmitter of one network node operates to transmit a CW optical signal together with legacy data-carrying optical signals. At another network node, a low-complexity, low-latency coherent optical receiver is used to obtain time-resolved measurements of the Stokes parameters of the CW optical signal. The signal-processing chain of the optical receiver employs digital filtering to select frequency components of the measurements streams corresponding to seismic disturbances of the fiber-optical cable connecting the nodes. The selected frequency components are then used to compute values of an earthquake indicator, which are reported to a network controller. Based on such reports from three or more nodes, the network controller can determine the epicenter and magnitude of the earthquake and, if warranted, may generate a tsunami forecast.

System and methods of random noise attenuation are provided. A first model may be trained to extract random noise from seismic datasets. A second model may be trained to reconstruct leaked signals from the random noise extracted by the first model. A seismic dataset corresponding to a subsurface reservoir formation and including random noise may be obtained. Using the trained first model, at least a portion of the random noise may be extracted from the first seismic dataset. Using the trained second model, a leaked signal, which includes a portion of the seismic dataset, may be reconstructed from the extracted random noise. A cleaned seismic dataset is generated based on the reconstructed leaked signal and the extracted random noise. The cleaned seismic dataset may include a quantity of random noise that is less than that of the original seismic dataset.

The present disclosure is related to methods, systems, and machine-readable media for interference attenuation of a residual portion of seismic data, such as may be recorded in a marine seismic survey. Recorded seismic data can be separated into a portion attributed to a source and a residual portion. Seismic interference attenuation can be performed on the residual portion.

Systems, methods, and computer-readable media for attenuating guided waves in seismic data using polarization filtering are provided. A raw hydrophone component and raw geophone component of multicomponent seismic data may be scaled using a constant scalar to enhance the ellipticity ratio of guided waves. Polarization filtering based on the ellipticity ratio may be applied within a velocity constraint to the scaled hydrophone and vertical geophone components to attenuate the guided waves. Additionally or alternatively, polarization filtering based on the tilt angle may be applied within a velocity constraint to the raw hydrophone and vertical geophone components to attenuate the guided waves. Polarization filtering may be applied to a raw hydrophone component and raw vertical geophone component of seismic data to attenuate Scholte waves before attenuation of the guided waves.

Methods, systems, and apparatuses are disclosed for sensing acoustic waves in a medium. One example system includes a first elongated member, a first motion sensor sensitive to vibrations of the first elongated member, a second motion sensor spaced apart from the first motion sensor and also sensitive to vibrations of the first elongated member, and a first vibration source operably coupled to the first elongated member and configured to vibrate the first elongated member.