The disclosure relates to a method and system for downhole processing of data, such as images, including using a set of downhole sensors to measure parameters relative to the borehole at a plurality of depths and azimuths and detecting predetermined features of the borehole, using a downhole processor, with a trained machine-learning model and extracting characterization data, characterizing the shape and position of the predetermined features that are transmitted to the surface. It also provides a method and system for providing an image of a geological formation at the surface including transmitting a first dataset to the surface that will be used for reconstructing an image at the surface, downhole processing of a second dataset to detect predetermined features and extract characterization data that are transmitted at the surface and displaying a combined image comprising the predetermined features overlaid on the first image.

Reducing casing wave effects on sonic logging data by positioning two or more receivers in a borehole in a subsurface formation; receiving, at two or more receivers in a borehole in a subsurface formation, a first signal associated with a first acoustic signal originating from a first transmitter position; receiving, at the two or more receivers, a second signal associated with a second acoustic signal originating from a second transmitter position; creating a dataset based on the first signal and the second signal; identifying casing wave signals in the dataset based at least in part on the second signal; calculating inverse-phase casing wave signals based at least in part on the casing wave signals and the second signal; and reducing effects of the casing wave signals on the dataset using the inverse-phase casing wave signals.

Reducing casing wave effects on sonic logging data by positioning two or more receivers in a borehole in a subsurface formation; receiving, at two or more receivers in a borehole in a subsurface formation, a first signal associated with a first acoustic signal originating from a first transmitter position; receiving, at the two or more receivers, a second signal associated with a second acoustic signal originating from a second transmitter position; creating a dataset based on the first signal and the second signal; identifying casing wave signals in the dataset based at least in part on the second signal; calculating inverse-phase casing wave signals based at least in part on the casing wave signals and the second signal; and reducing effects of the casing wave signals on the dataset using the inverse-phase casing wave signals.

A lithology prediction that uses a geological age model as an input to a machine learning model. The geological age model is capable of separating and recoding different seismic packages derived from the horizon interpretation. Once the machine learning model has been trained, a validation may be performed to determine the quality of the machine learning model. The quality may be improved by refining the training of the machine learning model. The lithology prediction generated by the machine learning model that utilizes the geological age model provides an improved lithology prediction that more accurately reflects the subterranean formation of an area of interest.

A lithology prediction that uses a geological age model as an input to a machine learning model. The geological age model is capable of separating and recoding different seismic packages derived from the horizon interpretation. Once the machine learning model has been trained, a validation may be performed to determine the quality of the machine learning model. The quality may be improved by refining the training of the machine learning model. The lithology prediction generated by the machine learning model that utilizes the geological age model provides an improved lithology prediction that more accurately reflects the subterranean formation of an area of interest.

An acoustic logging system includes a first transducer in contact with or in close proximity to a sound barrier configured to emit a beam of acoustic energy according to a first mode of operation or a second mode of operation. The system also includes one or more second transducers in contact with or in close proximity to the sound barrier, positioned axially away from the first transducer, configured to receive acoustic energy from a wellbore environment responsive to the beam. The first mode of operation is a transmit-receive mode of operation where the beam is steerable to interact with one or more wellbore components at a first angle and the second mode of operation is a pulse echo mode of operation where the beam interacts with the one or more wellbore components at a second angle different from the first angle.

An acoustic logging system includes a first transducer in contact with or in close proximity to a sound barrier configured to emit a beam of acoustic energy according to a first mode of operation or a second mode of operation. The system also includes one or more second transducers in contact with or in close proximity to the sound barrier, positioned axially away from the first transducer, configured to receive acoustic energy from a wellbore environment responsive to the beam. The first mode of operation is a transmit-receive mode of operation where the beam is steerable to interact with one or more wellbore components at a first angle and the second mode of operation is a pulse echo mode of operation where the beam interacts with the one or more wellbore components at a second angle different from the first angle.

A method for generating one or more reservoir models using machine learning is provided. Generating reservoir models is typically a time-intensive idiosyncratic process. However, machine learning may be used to generate one or more reservoir models that characterize the subsurface. The machine learning may use geological data, geological concepts, reservoir stratigraphic configurations, and one or more input geological models in order to generate the one or more reservoir models. As one example, a generative adversarial network (GAN) may be used as the machine learning methodology. The GAN includes two neural networks, including a generative network (which generates candidate reservoir models) and a discriminative network (which evaluates the candidate reservoir models), contest with each other in order to generate the reservoir models.

A method for generating one or more reservoir models using machine learning is provided. Generating reservoir models is typically a time-intensive idiosyncratic process. However, machine learning may be used to generate one or more reservoir models that characterize the subsurface. The machine learning may use geological data, geological concepts, reservoir stratigraphic configurations, and one or more input geological models in order to generate the one or more reservoir models. As one example, a generative adversarial network (GAN) may be used as the machine learning methodology. The GAN includes two neural networks, including a generative network (which generates candidate reservoir models) and a discriminative network (which evaluates the candidate reservoir models), contest with each other in order to generate the reservoir models.

A method and system method for determining motion of a downhole tool and feeding back drilling performance. The method may comprise taking a synchronous tool face measurement of the downhole tool, taking a synchronous pulse-echo acquisition to estimate a shape of a borehole, inputting at least the shape of the borehole, the center trajectory of the downhole tool, the rotational time of the downhole tool, the position of the downhole tool, and the one or more measurements of the downhole tool into an information fusion for drilling dynamics, identifying at least one of a whirl, a vibration, or a stick-slip of the downhole tool, and identifying one or more borehole condition and a drilling efficiency. A system may comprise a downhole tool, at least two transducers, and an information handling system.