A method is provided of inspecting a nested multi-layer structure including a first and second electrically conductive layer and a third layer disposed behind the second conductive layer. The method includes deploying a sensor device including an electromagnetic acoustic transducer to a borehole location proximate to the structure, generating a drive signal including a plurality of frequencies, applying an electrical current signal to the sensor device based on the drive signal and inducing currents in the first conductive layer that induce currents generating acoustic signals having the plurality of frequencies, detecting a first set of resonant frequencies based on received electromagnetic signals, detecting a second set of resonant frequencies based on received acoustic signals, estimating a property of the first and/or the second conductive layer based on the first set of resonant frequencies, and estimating a property of the third layer based on the second set of resonant frequencies.

A method for enhancing properties of geophysical data with deep learning networks. Geophysical data may be acquired by positioning a source of sound waves at a chosen shot location, and measuring back-scattered energy generated by the source using receivers placed at selected locations. For example, seismic data may be collected using towed streamer acquisition in order to derive subsurface properties or to form images of the subsurface. However, towed streamer data may be deficient in one or more properties (e.g., at low frequencies). To compensate for the deficiencies, another survey (such as an Ocean Bottom Nodes (OBN) survey) may be sparsely acquired in order to train a neural network. The trained neural network may then be used to compensate for the towed streamer deficient properties, such as by using the trained neural network to extend the towed streamer data to the low frequencies.

Disclosed are systems and methods for selecting modes and frequencies of interest in a slowness-frequency map of sonic logging information. These include measuring, by a sonic logging tool, sonic data within a borehole, determining a frequency range for a selected mode of the sonic data, determining a slowness range for the selected mode of the sonic data, applying the frequency range and the slowness range to the sonic data to select a subset of data from the sonic data, processing the selected subset of data.

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.

A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.

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.

A method of generating target-oriented acquisition-imprint-free prestack angle gathers using common focus point (CFP) operators includes receiving a plurality of seismic traces associated with a target point in a reservoir. A first angle domain common image gather (ADCIG) is generated based on the received plurality of seismic traces. A plurality of synthetic traces associated with the target point is generated. A second ADCIG is generated based on the synthetic traces. An enhanced ADCIG is generated using the first ADCIG and the second ADCIG.

A method of determining fluid inflow rates within a wellbore comprises determining a plurality of temperature features from a distributed temperature sensing signal originating in a wellbore, determining one or more frequency domain features from an acoustic signal originating the wellbore, and using at least one temperature feature of the plurality of temperature features and at least one frequency domain feature of the one or more frequency domain features to determine a fluid inflow rate at one or more locations along the wellbore.

Disclosed are methods, systems, and computer-readable medium to perform operations including: decomposing the seismic data into a plurality of sub-volumes, each sub-volume associated with a respective one of the plurality of frequency components; identifying a portion of the seismic data that includes one or more multiples, the multiples being seismic data associated with multiply reflected seismic energy; identifying, based on the plurality of sub-volumes, the one or more multiples within the portion of the seismic data; and determining, from the plurality of frequency components, a single frequency that gives rise to a predetermined continuity along a primary reflector affected by the one or more multiples.

Various embodiments include methods and apparatus structured to investigate a structure of multiple strings of pipe in a wellbore and material around the pipes in the wellbore. An array of acoustic receivers can be used to monitor sound energy from the structure and material within and around the structure. The received sound energy can be segregated and coherent signal processing of the received sound energy can be conducted with respect to location. A bond map of the structure and regions around the multiple strings of pipe can be derived from the coherent signal processing. Additional apparatus, systems, and methods can be implemented in a variety of applications.