Methods and systems for increasing the recovery efficiency of a petroleum reservoir. For example, a method for performing a petroleum recovery assessment to increase the recovery efficiency of a petroleum reservoir includes evaluating results associated with a reservoir management analysis for the petroleum reservoir and generating a reservoir management analysis score. The method further includes evaluating results associated with a global benchmark analysis and generating an estimated maximum recovery efficiency for the petroleum reservoir. The method further includes determining key recovery obstacles impeding the petroleum reservoir from achieving the estimated maximum recovery efficiency, and identifying field development opportunities addressing a key recovery obstacle that when implemented, increases a recovery efficiency for the petroleum reservoir closer to the estimated maximum recovery efficiency.

A method is provided for automatically classifying grains, pores, or both of a formation sample. The method includes receiving a digital image representation of the formation sample, and identifying a plurality of pores, grains, or both in the digital image representation. The method also includes computing a plurality of geometric features associated with the pores, grains, or both in the digital image representation, and inputting the geometric features into an unsupervised machine learning model. The unsupervised machine learning model determines a label for each identified pore and grain, the label being a pore-type or a grain-type, and the plurality of geometric features and the labels determined for each pore, grain, or both, are input into a supervised machine learning model. The supervised machine learning model determines a final classification of a pore-type for each pore and a grain-type for each grain in the digital image representation of the formation sample.

A method is provided for automatically classifying grains, pores, or both of a formation sample. The method includes receiving a digital image representation of the formation sample, and identifying a plurality of pores, grains, or both in the digital image representation. The method also includes computing a plurality of geometric features associated with the pores, grains, or both in the digital image representation, and inputting the geometric features into an unsupervised machine learning model. The unsupervised machine learning model determines a label for each identified pore and grain, the label being a pore-type or a grain-type, and the plurality of geometric features and the labels determined for each pore, grain, or both, are input into a supervised machine learning model. The supervised machine learning model determines a final classification of a pore-type for each pore and a grain-type for each grain in the digital image representation of the formation sample.

A method of mud logging is disclosed which the chemical constituents and concentrations of formation fluid are calculated based on pulse power plasma parameters and the constituent species and concentrations of drilling mud, including reaction products, upon which the pulse power plasma has acted. Based on correlation between pulse power plasma parameters, including drilling parameters, drilling can be optimized for identified formation and formation fluid species. An offset between the chemical makeup of the drilling mud exposed to pules power plasma and the chemical makeup of formation fluid is calculated. Based on the calculated offset, pulse power plasma drilling can be controlled as a function of drilling mud concentration including in other wellbores in the formation or field.

A method of mud logging is disclosed which the chemical constituents and concentrations of formation fluid are calculated based on pulse power plasma parameters and the constituent species and concentrations of drilling mud, including reaction products, upon which the pulse power plasma has acted. Based on correlation between pulse power plasma parameters, including drilling parameters, drilling can be optimized for identified formation and formation fluid species. An offset between the chemical makeup of the drilling mud exposed to pules power plasma and the chemical makeup of formation fluid is calculated. Based on the calculated offset, pulse power plasma drilling can be controlled as a function of drilling mud concentration including in other wellbores in the formation or field.

A method may include measuring a formation sample using a Raman spectrometer to determine a formation sample characteristic, wherein the formation sample characteristic is mineral ID and distribution, carbon ID and distribution, thermal maturity, rock texture, fossil characterization, or combinations thereof.

A method may include measuring a formation sample using a Raman spectrometer to determine a formation sample characteristic, wherein the formation sample characteristic is mineral ID and distribution, carbon ID and distribution, thermal maturity, rock texture, fossil characterization, or combinations thereof.

A power control device includes a communication device configured to be disposed in a borehole and configured to couple electrical power from a power source to a downhole component from a conductor disposed along a borehole string, a circuit breaker system including a first circuit breaker disposed at a connection between the conductor and the downhole component and configured to be closed to connect the downhole component to the conductor, and a controller configured to monitor at least one of a current level and a voltage level at the connection and at the conductor. The controller is configured to control the circuit breaker system and autonomously perform opening the first circuit breaker in response to detecting a deviation in the at least one of the current levels and voltage levels at the connection, to isolate the downhole component from the conductor and the power source.

Methods and systems for optimizing drilling operations in a wellbore using a drill string are provided. The methods and systems include measuring a first formation characteristic with at least one sensor, measuring a second formation characteristic by means of a hydraulic test, the at least one second formation characteristic being different from the at least one first formation characteristic, generating a model to represent a formation around the wellbore, the model incorporating the first formation characteristic and the second formation characteristic, and performing a drilling operation based on the generated model.

A system for monitoring coring operations has a sensor 80 for detecting one or more drilling parameters relating to a down-the-hole coring operation. An indicative signal from the sensor is communicated to a signal transmitter (30) for transmitting the indicative signal to the surface. The signal transmitter is located in or adjacent the coring assembly. The signal transmitter can be a mud pulser (30) housed above a core barrel (14). Communication of the indicative signal to the signal transmitter can be wireless, hard wired or conducted through the material of an outer barrel (12) of a drilling assembly. The core barrel can include a core limit recognition/detection device (34). An adapter/sub (90) incorporates a check valve (92) to relieve excess fluid pressure if there is sufficient hydraulic lock immediately above a core sample within the core barrel as the core sample enters the core barrel.