Abstract: A method for drilling includes obtaining formation-measurement pairings, training a machine-learning model using the formation-measurement pairings, receiving measurements obtained by a tool positioned in a well formed in a formation, and generating a formation model of at least a portion of the formation using the machine-learning model and the measurements. The formation model represents one or more physical parameters of the formation, one or more structural parameters of the formation, or both.

Abstract: Methods capable of determining a depth of investigation of a logging tool can include generating an error distribution model for a logging tool. The methods can also include defining a detection threshold above which a measured signal from a measurement channel of the logging tool can be considered reliable based on output from the error distribution model, and generating a simulated formation model to determine the depth of investigation. The depth of investigation can be biased by the detection threshold.

Abstract: A method for making gain compensated electromagnetic logging measurements of a subterranean formation includes rotating an electromagnetic logging tool in a subterranean wellbore. The logging tool includes a transmitter having at least one transmitting antenna axially spaced apart from a receiver having at least one receiving antenna. Electromagnetic waves are transmitted into the subterranean wellbore using the at least one transmitting antenna. Voltage measurements corresponding to the transmitted electromagnetic waves are received at the receiving antenna. The voltage measurements are processed to compute real and imaginary directional resistivity measurement quantities.

Abstract: A method for drilling includes obtaining formation-measurement pairings, training a machine-learning model using the formation-measurement pairings, receiving measurements obtained by a tool positioned in a well formed in a formation, and generating a formation model of at least a portion of the formation using the machine-learning model and the measurements. The formation model represents one or more physical parameters of the formation, one or more structural parameters of the formation, or both.

Abstract: A drill string can include an electromagnetic transmitter oriented at an actual effective tilt angle with respect to the drill string and an electromagnetic receiver oriented at an actual effective tilt angle with respect to the drill string. The transmitter and received can be used to investigate geologic formations surrounding the drill string, and measurements of the geologic formations can be based on the actual effective tilt angles of the transmitter and the receiver.

Abstract: A method for making gain compensated electromagnetic logging measurements of a subterranean formation includes rotating an electromagnetic logging tool in a subterranean wellbore. The logging tool includes a transmitter having at least one transmitting antenna axially spaced apart from a receiver having at least one receiving antenna. Electromagnetic waves are transmitted into the subterranean wellbore using the at least one transmitting antenna. Voltage measurements corresponding to the transmitted electromagnetic waves are received at the receiving antenna. The voltage measurements are processed to compute real and imaginary directional resistivity measurement quantities.

Abstract: Methods capable of determining a depth of investigation of a logging tool can include generating an error distribution model for a logging tool. The methods can also include defining a detection threshold above which a measured signal from a measurement channel of the logging tool can be considered reliable based on output from the error distribution model, and generating a simulated formation model to determine the depth of investigation. The depth of investigation can be biased by the detection threshold.