Systems, methods, and computer-readable media for in-situ calibration of magnetic field measurements. In some examples, a method can involve generating a magnetic field via a magnetic field source that is coupled to a downhole tool. The magnetic field source can be located within a fixed distance from one or more sensors coupled to the downhole tool. The method can also involve obtaining respective field measurements of the known magnetic field from the one or more sensors, and comparing the respective field measurements from the one or more sensors with respective reference measurements previously obtained from the one or more sensors to yield respective comparisons. The method can then involve determining, based on the respective comparisons, a respective sensitivity drift for each of the one or more sensors.

Systems, methods, and computer-readable media for in-situ calibration of magnetic field measurements. In some examples, a method can involve generating a magnetic field via a magnetic field source that is coupled to a downhole tool. The magnetic field source can be located within a fixed distance from one or more sensors coupled to the downhole tool. The method can also involve obtaining respective field measurements of the known magnetic field from the one or more sensors, and comparing the respective field measurements from the one or more sensors with respective reference measurements previously obtained from the one or more sensors to yield respective comparisons. The method can then involve determining, based on the respective comparisons, a respective sensitivity drift for each of the one or more sensors.

The subject disclosure provides for a method of optical sensor calibration implemented with neural networks through machine learning to make real-time optical fluid answer product prediction adapt to optical signal variation of synthetic and actual sensor inputs integrated from multiple sources. Downhole real-time fluid analysis can be performed by monitoring the quality of the prediction with each type of input and determining which type of input generalizes better. The processor can bypass the less robust routine and deploy the more robust routine for remainder of the data prediction. Operational sensor data can be incorporated from a particular optical tool over multiple field jobs into an updated calibration when target fluid sample compositions and properties become available. Reconstructed fluid models adapted to prior field job data, in the same geological or geographical area, can maximize the likelihood of quality prediction on future jobs and optimize regional formation sampling and testing applications.

The subject disclosure provides for a method of optical sensor calibration implemented with neural networks through machine learning to make real-time optical fluid answer product prediction adapt to optical signal variation of synthetic and actual sensor inputs integrated from multiple sources. Downhole real-time fluid analysis can be performed by monitoring the quality of the prediction with each type of input and determining which type of input generalizes better. The processor can bypass the less robust routine and deploy the more robust routine for remainder of the data prediction. Operational sensor data can be incorporated from a particular optical tool over multiple field jobs into an updated calibration when target fluid sample compositions and properties become available. Reconstructed fluid models adapted to prior field job data, in the same geological or geographical area, can maximize the likelihood of quality prediction on future jobs and optimize regional formation sampling and testing applications.

The disclosed embodiments include a rotating survey tool. The rotating survey tool includes a first sensor array that in operation collects a first set of survey measurements during a downhole drilling operation. Additionally, the rotating survey tool includes a second sensor array directly coupled to the first sensor array that in operation collects a second set of survey measurements while a drill bit drills during the downhole drilling operation. Further, the second set of survey measurements has a greater base accuracy than the first set of survey measurements.

The disclosed embodiments include a rotating survey tool. The rotating survey tool includes a first sensor array that in operation collects a first set of survey measurements during a downhole drilling operation. Additionally, the rotating survey tool includes a second sensor array directly coupled to the first sensor array that in operation collects a second set of survey measurements while a drill bit drills during the downhole drilling operation. Further, the second set of survey measurements has a greater base accuracy than the first set of survey measurements.

Systems and methods of the present disclosure relate to calibration of a resistivity tool. A method for in-situ calibration of a resistivity logging tool, comprises transmitting signals with transmitters of the resistivity logging tool; measuring voltages at two or more receivers located at different distances to the transmitters of the resistivity logging tool; decoupling two or more sets of multi-component tensors at two or more receivers based on the measured voltages; calculating a ratio signal from two or more sets of multi-component tensors; obtaining an apparent resistivity based on the ratio signal; simulating a dipole response tensor at the first receiver based on the apparent resistivity; comparing the first set of multi-component tensor with the dipole response tensor to acquire an in-situ calibration factor; and applying the in-situ calibration factor to multi-components for an inversion input.

Systems and methods of the present disclosure relate to calibration of a resistivity tool. A method for in-situ calibration of a resistivity logging tool, comprises transmitting signals with transmitters of the resistivity logging tool; measuring voltages at two or more receivers located at different distances to the transmitters of the resistivity logging tool; decoupling two or more sets of multi-component tensors at two or more receivers based on the measured voltages; calculating a ratio signal from two or more sets of multi-component tensors; obtaining an apparent resistivity based on the ratio signal; simulating a dipole response tensor at the first receiver based on the apparent resistivity; comparing the first set of multi-component tensor with the dipole response tensor to acquire an in-situ calibration factor; and applying the in-situ calibration factor to multi-components for an inversion input.

A method of detecting an event by: obtaining a first sample data set; determining a frequency domain feature(s) of the first sample data set over a first time period; determining a first threshold for the a frequency domain feature(s) using the first sample data set; determining that the frequency domain feature(s) matches the first threshold; determining the presence of an event during the first time period based on determining that the frequency domain feature(s) matches the first threshold; obtaining a second sample data set; determining a frequency domain feature(s) of the second sample data set over a second time period; determining a second threshold for the frequency domain feature(s) using the second sample data set; determining that the frequency domain feature(s) matches the second threshold; and determining the presence of the event during the second time period based on determining that the frequency domain feature(s) matches the second threshold.

A method of detecting an event by: obtaining a first sample data set; determining a frequency domain feature(s) of the first sample data set over a first time period; determining a first threshold for the a frequency domain feature(s) using the first sample data set; determining that the frequency domain feature(s) matches the first threshold; determining the presence of an event during the first time period based on determining that the frequency domain feature(s) matches the first threshold; obtaining a second sample data set; determining a frequency domain feature(s) of the second sample data set over a second time period; determining a second threshold for the frequency domain feature(s) using the second sample data set; determining that the frequency domain feature(s) matches the second threshold; and determining the presence of the event during the second time period based on determining that the frequency domain feature(s) matches the second threshold.