Aspects of the subject technology relate to determining a holdup measurement based on a gamma spectrum through machine learning. A spectral image based on a gamma spectrum generated downhole in a wellbore can be accessed. A component of a holdup measurement for the wellbore can be classified into a specific quantized level through application of a machine learning classification model to the spectral image. A continuous value for the component of the holdup measurement for the wellbore can be quantified by applying a machine learning quantization model associated with the quantized level.

A method for determining a distribution of a uranium deposit is provided, including: acquiring a remote detection result of a target area; acquiring a chemical detection result of soil in the target area; delineating a plurality of exploration regions in the target area according to the remote detection result and the chemical detection result; and providing boreholes in the plurality of exploration regions for gamma detection to determine a distribution and a trend of a uranium deposit according to a result of the gamma detection.

A method for determining a distribution of a uranium deposit is provided, including: acquiring a remote detection result of a target area; acquiring a chemical detection result of soil in the target area; delineating a plurality of exploration regions in the target area according to the remote detection result and the chemical detection result; and providing boreholes in the plurality of exploration regions for gamma detection to determine a distribution and a trend of a uranium deposit according to a result of the gamma detection.

A method may include obtaining, by a computer processor, seismic data regarding a geological region of interest. The method may further include obtaining, by the computer processor, well log data from a wellbore within the geological region of interest. The method may further include determining, by the computer processor, a formation top depth using the seismic data, the well log data, a stratigraphic column, and a machine-learning model. The stratigraphic column may describe an order of various formations within the geological region of interest. The machine-learning model may assign a feature among the seismic data and the well log data to a formation among the formations in the stratigraphic column to determine the formation top depth.

A method may include obtaining, by a computer processor, seismic data regarding a geological region of interest. The method may further include obtaining, by the computer processor, well log data from a wellbore within the geological region of interest. The method may further include determining, by the computer processor, a formation top depth using the seismic data, the well log data, a stratigraphic column, and a machine-learning model. The stratigraphic column may describe an order of various formations within the geological region of interest. The machine-learning model may assign a feature among the seismic data and the well log data to a formation among the formations in the stratigraphic column to determine the formation top depth.

A spectrometer for downhole applications can be calibrated without using radioactive sources. A spectrum of measured gamma ray counts can be received from a spectrometer in a calibration mode. A spectrum-to-window ratio can be used to determine a relationship between voltage level applied to a photoreceptor of the spectrometer and gain factors. A voltage level associated with a gain factor of one can be identified for use by the spectrometer in a non-calibration mode. The measured gamma ray counts and reference shapes for a plurality of radioactive elements can be used in a least squares fit process to determine an offset to apply to the spectrometer in the non-calibration mode.

A spectrometer for downhole applications can be calibrated without using radioactive sources. A spectrum of measured gamma ray counts can be received from a spectrometer in a calibration mode. A spectrum-to-window ratio can be used to determine a relationship between voltage level applied to a photoreceptor of the spectrometer and gain factors. A voltage level associated with a gain factor of one can be identified for use by the spectrometer in a non-calibration mode. The measured gamma ray counts and reference shapes for a plurality of radioactive elements can be used in a least squares fit process to determine an offset to apply to the spectrometer in the non-calibration mode.

Aspects of the subject technology relate to a system configured to apply a voltage setting to a sensor of a downhole tool. The system is configured to identify an active gain control model for a temperature-sensitive sensor for a downhole tool, receiving temperature data for the downhole tool, and apply a high voltage setting for the first sensor based on the temperature data and the active gain control model. The system is further configured to collect sensor data from the sensor operating in a wellbore using the high voltage setting and update the active gain control model based on the sensor data.

Aspects of the subject technology relate to a system configured to apply a voltage setting to a sensor of a downhole tool. The system is configured to identify an active gain control model for a temperature-sensitive sensor for a downhole tool, receiving temperature data for the downhole tool, and apply a high voltage setting for the first sensor based on the temperature data and the active gain control model. The system is further configured to collect sensor data from the sensor operating in a wellbore using the high voltage setting and update the active gain control model based on the sensor data.

A method for making natural gamma ray measurements includes deploying a logging while drilling tool including an electrical neutron output of the electrical neutron source is modulated and the natural gamma ray sensor is used to make a corresponding gamma ray measurement during at least a portion of the modulation. The gamma ray measurement is processed to obtain a corrected total natural gamma ray measurement of the subterranean formation.