A sonic logging method is provided that transmits acoustic signals using a high order acoustic source and processes waveform data to identify a set of arrival events and time picks by automatic and/or manual methods. Ray tracing inversion is carried out for each arrival event over a number of possible raypath types that include at least one polarized shear raypath type to determine two-dimensional reflector positions and predicted inclination angles of the arrival event for the possible raypath types. One or more three-dimensional slowness-time coherence representations are generated for the arrival event and raypath type(s) and evaluated to determine azimuth, orientation and raypath type of a corresponding reflector. The method outputs a three-dimensional position and orientation for at least one reflector. The information derived from the method can be conveyed in various displays and plots and structured formats for reservoir understanding and also output for use in reservoir analysis and other applications.

Deconvolution-based processing of ultrasonic waveforms enables robust calculation of two-way travel time for an ultrasonic caliper, particularly in the presence of multiple, proximal reflectors (e.g., mud cake, formation, casing, cement, etc.).

Deconvolution-based processing of ultrasonic waveforms enables robust calculation of two-way travel time for an ultrasonic caliper, particularly in the presence of multiple, proximal reflectors (e.g., mud cake, formation, casing, cement, etc.).

A method includes receiving geophysical data representative of a geophysical structure; providing the geophysical data as one or more input data to a neural network; training the neural network to reconstruct the geophysical structure that was received and provide one or more uncertainty metrics for one or more features of the geophysical structure that is reconstructed; reconstructing, using the neural network that has been trained, the geophysical structure;

and determining, using the neural network that has been trained, the one or more uncertainty metrics by implementing a second drop out condition on the one or more nodes of the one or more hidden layers of the neural network. The training is performed at least partially by implementing a first drop out condition on one or more nodes of one or more hidden layers of the neural network to randomly set an output of the one or more nodes to zero.

A method includes receiving geophysical data representative of a geophysical structure; providing the geophysical data as one or more input data to a neural network; training the neural network to reconstruct the geophysical structure that was received and provide one or more uncertainty metrics for one or more features of the geophysical structure that is reconstructed; reconstructing, using the neural network that has been trained, the geophysical structure;

and determining, using the neural network that has been trained, the one or more uncertainty metrics by implementing a second drop out condition on the one or more nodes of the one or more hidden layers of the neural network. The training is performed at least partially by implementing a first drop out condition on one or more nodes of one or more hidden layers of the neural network to randomly set an output of the one or more nodes to zero.

A method for determining change in stress in a reservoir formation includes inducing a pressure pulse in a first well hydraulically connected by a fracture to the reservoir formation. A stress-related attribute of the fracture is determined from reflection events detected in pressure measurement made in the first well as a result of the inducing the pressure pulse. The inducing and determining are repeated to estimate changes in the stress-related attribute with respect to time. A method for determining and localizing type of interaction between a treated well and an observation well by monitoring pressure and fracture changes in the observation well.

A system includes different types of downhole sensing tools deployed in a borehole, wherein the different types of downhole sensing tools are optimized to identify a downhole condition based on a predetermined downhole evaluation plan that accounts for sensing tool availability and performance constraints. The system also includes at least one processing unit configured to analyze measurements collected by the different types of downhole sensing tools, wherein the collected measurements are analyzed together to identify the downhole condition. The system also includes at least one device that performs an operation in response to the identified downhole condition.

A system includes different types of downhole sensing tools deployed in a borehole, wherein the different types of downhole sensing tools are optimized to identify a downhole condition based on a predetermined downhole evaluation plan that accounts for sensing tool availability and performance constraints. The system also includes at least one processing unit configured to analyze measurements collected by the different types of downhole sensing tools, wherein the collected measurements are analyzed together to identify the downhole condition. The system also includes at least one device that performs an operation in response to the identified downhole condition.

Certain aspects of the present disclosure relate to calibrating a formation signal for a mixed set measurement device. A first air-hang response of a first measurement device for a tubular string associated with a drilling operation can be measured. A second air-hang response of a second measurement device for the tubular string associated with the drilling operation can be measured. The first air-hang response and the second air-hang response can be used to determine a mixed air-hang response of the mixed set measurement device. The mixed air-hang response can be used to calibrate a formation signal for the mixed set measurement device.

A method for well log data interpretation includes obtaining well data by a well log interpreter and determining, automatically by the well log interpreter, a plurality of machine-learning models corresponding to the well data based on a plurality of well data type. Additionally, the method includes determining, by the well log interpreter and in real-time, preview data regarding a well operation using the machine-learning models, and transmitting, by the well log interpreter to a user device, an interpretation report comprising the preview data. A system for well log data interpretation includes a logging system coupled to a plurality of logging tools, a logging system coupled to a plurality of logging tools, a drilling system coupled to the logging system, and a well log interpreter comprising a computer processor. The well log interpreter is coupled to the logging system and the drilling system. The well log interpreter comprising functionality for performing the well log data interpretation method.