A system can apply an unsupervised machine-learning model to ultrasonic waveform data received about a wellbore for identifying channels in the wellbore. A system can receive ultrasonic waveform data about a wellbore using an arrangement of transducers positionable in the wellbore. The ultrasonic waveform data can include a set of ultrasonic waveforms. The system can generate a set of attributes for each ultrasonic waveform of the set of ultrasonic waveforms. The system can apply an unsupervised machine-learning model to the set of ultrasonic waveforms for clustering the set of attributes of ultrasonic waveform into a set of clusters. The system can output the set of clusters for categorizing the ultrasonic waveform data.

A system can apply an unsupervised machine-learning model to ultrasonic waveform data received about a wellbore for identifying channels in the wellbore. A system can receive ultrasonic waveform data about a wellbore using an arrangement of transducers positionable in the wellbore. The ultrasonic waveform data can include a set of ultrasonic waveforms. The system can generate a set of attributes for each ultrasonic waveform of the set of ultrasonic waveforms. The system can apply an unsupervised machine-learning model to the set of ultrasonic waveforms for clustering the set of attributes of ultrasonic waveform into a set of clusters. The system can output the set of clusters for categorizing the ultrasonic waveform data.

A model is used to generate corrections to mitigate ideal condition artifacts in acoustic property values of an annular material in a cased wellbore. A mathematical model that generates acoustic property values at ideal conditions introduces artifacts into the acoustic property values. Acoustic measurements of an annular material are used to generate features that represent wellbore conditions and are not accounted for in the mathematical model that generates acoustic property values. A model will generate corrections for acoustic property values of an annular material with the features to yield a more accurate acoustic property profile for the annular material of a cased hole.

In some embodiments, a method includes conveying a downhole tool in a tubing, positioned in a casing which forms an annulus between the casing and a wellbore formed in a subsurface formation, the downhole tool having a rotatable transmitter and a receiver array. The method includes performing the following until an acoustic transmission has been emitted for each of a number of defined azimuthal positions: rotating the rotatable transmitter to one of the number of defined azimuthal positions, emitting the acoustic transmission, and detecting, by the receiver array and without rotation of the downhole tool beyond a rotation threshold, an acoustic response of a number of acoustic responses that is derived from the acoustic transmission. The method further includes computationally rotating, by a processor and after detecting, data of each of the number of acoustic responses in a pre-determined direction to generate a computationally rotated multipole response.

A method includes receiving well log data for a plurality of wells. A flag is generated based at least partially on the well log data. The wells are sorted into groups based at least partially on the well log data, the flag, or both. A model is built for each of the wells based at least partially on the well log data, the flag, and the groups.

Systems and methods are provided for determining a formation body wave slowness from an acoustic wave. Waveform data is determined by logging tool measuring the acoustic wave. Wave features are determined from the waveform data and a model is applied to the wave features to determine data-driven scale factors The data-driven scale factors can be used to determine a body wave slowness within a surrounding borehole environment and the body wave slowness can be used to determine formation characteristics of the borehole environment.

Systems and methods are provided for determining a formation body wave slowness from an acoustic wave. Waveform data is determined by logging tool measuring the acoustic wave. Wave features are determined from the waveform data and a model is applied to the wave features to determine data-driven scale factors The data-driven scale factors can be used to determine a body wave slowness within a surrounding borehole environment and the body wave slowness can be used to determine formation characteristics of the borehole environment.

In at least one embodiment, a well inspection method and system enables transmission of an acoustic signal from a well inspection tool into a well structure and reception of return signals from the well structure at an array of receivers on the well inspection tool. The method and system enable performing of Short-Term Fourier Transform (STFT) on the return signals to generate spectrogram data that is used to determine short-term power spectra of the return signals. Time-dependent frequency response and location-dependent waveform propagation patterns are identified from the short-term power spectra. Cement bonding conditions is determined based on pattern matching using the time-dependent frequency response patterns and using the location-dependent waveform propagation patterns.

A system and method for determining an uncertainty of a distance to bed boundary (DTBB) inversion of a geologic formation. The system or method includes receiving logging data from a borehole tool, performing a first DTBB inversion using the logging data to calculate first DTBB solutions, adding quantified noise to the logging data to produce an adjusted signal, performing a second DTBB inversion using the adjusted signal to calculate second DTBB solutions, comparing the first DTBB solutions to the second DTBB solutions to determine an uncertainty of the first DTBB solutions based on a relationship of the quantified noise and the difference between the first DTBB solutions and the second DTBB solutions.

A system and method for determining an uncertainty of a distance to bed boundary (DTBB) inversion of a geologic formation. The system or method includes receiving logging data from a borehole tool, performing a first DTBB inversion using the logging data to calculate first DTBB solutions, adding quantified noise to the logging data to produce an adjusted signal, performing a second DTBB inversion using the adjusted signal to calculate second DTBB solutions, comparing the first DTBB solutions to the second DTBB solutions to determine an uncertainty of the first DTBB solutions based on a relationship of the quantified noise and the difference between the first DTBB solutions and the second DTBB solutions.