Emerging Techniques in Measuring Capillary Pressure and Permeability Using NMR and AI

Measurement of Special Core Analysis (SCAL) parameters is a costly and time-intensive process. Some of the disadvantages of the current techniques are that they are not performed in-situ, and can destroy the core plugs, e.g., mercury injection capillary pressure (MICP). The objective of this paper is to introduce and investigate the emerging techniques in measuring SCAL parameters using Nuclear Magnetic Resonance (NMR) and Artificial Intelligence (Al). The conventional methods for measuring SCAL parameters are well understood and are an industry standard. Yet, NMR and Al - which are revolutionizing the way petroleum engineers and scientists describe rock/fluid properties - have yet to be utilized to their full potential in reservoir description. In addition, integration of the two tools will open a greater opportunity in the field of reservoir description, where measurement of in-situ SCAL parameters could be achieved. This paper shows the results of NMR lab experiments and Al analytics for measuring capillary pressures and permeability. The data set was divided into 70% for training and 30% for validation. Artificial Neural Network (ANN) was used and the developed model compared well with the permeability and capillary pressure data measured from the conventional methods. Specifically, the model predicted permeability 10% error. Similarly, for the capillary pressures, the model was able to achieve an excellent match. This active research area of prediction of capillary pressure, permeability and other rock properties is a promising emerging technique that capitalizes on NMR/AI analytics. There is significant potential is being able to evaluate wettability in-situ. Core-plugs undergoing Amott-Harvey experiment with NMR measurements in the process can be used as a building block for an NMR/AI wettability determination technique. This potential aspect of NMR/AI analytics can have significant implications on field development and EOR projects The developed NMR-Al model is an excellent start to measure permeability and capillary pressure in-situ. This novel approach coupled with ongoing research for better handling of in-situ wettability measurement will provide the industry with enormous insight into the in-situ SCAL measurements which are currently considered as an elusive measurement with no robust logging technique to evaluate them in-situ.

Application of Micro-resistivity Scanning Imaging Logging Data in Reservoir Thickness Division

Reservoir parameter interpretation is one of the main contents of reservoir description, which affects the whole process of oilfield development. According to the characteristics of micro-resistivity scanning imaging logging, which can directly reflect the changes of lithology and physical properties of reservoirs, this paper compares the thickness and interbed division of reservoirs with conventional logging data, this paper finds out the shortcomings of the conventional logging data in the interpretation of thickness and the division of interlayers, and combines the core analysis data to examine the differences in the correlation on the coring wells, and obtains good results, it has laid the foundation for the establishment of new interpretation procedure.

Expanding the Envelope of Fiber-Optic Sensing for Reservoir Description and Dynamics

Fiber-optic sensing (FOS) technology is gradually becoming a pervasive tool in the monitoring and surveillance toolkit for reservoir engineers. Traditionally, sensing with fiber optic technology in the form of distributed temperature sensing (DTS) or distributed acoustic sensing (DAS), and most recently distributed strain sensing (DSS), distributed flow sensing (DFS) and distributed pressure sensing (DPS) were done with the fiber being permanently clamped either behind the casing or production tubing. Distributed chemical sensing (DCS) is still in the development phase. The emergence of the composite carbon-rod (CCR) system that can be easily deployed in and out of a well, similar to wireline logging, has opened up a vista of possibilities to obtain many FOS measurements in any well without prior fiber-optic installation. Currently, combinations of distributed FOS data are being used for injection management, well integrity monitoring, well stimulation and production performance optimization, thermal recovery management, etc. Is it possible to integrate many of the distributed FOS measurements in the CCR or a hybrid combination with wireline to obtain multiple measurements with one FOS cable? Each one of FOS has its own use to get certain data, or combination of FOS can be used to make a further interpretation. This paper reviews the state of the art of the FOS technology and the gamut of current different applications of FOS data in the oil and gas (upstream) industry. We present some results of traditional FOS measurements for well integrity monitoring, assessing production and injection flow profile, cross flow behind casing, etc. We propose some nontraditional applications of the technology and suggest a few ways through. Which the technology can be deployed for obtaining some key reservoir description and dynamics data for reservoir performance optimization.

On a Deep Learning Method of Estimating Reservoir Porosity

Porosity is an important parameter for the oil and gas storage, which reflects the geological characteristics of different historical periods. The logging parameters obtained from deep to shallow strata show the stratigraphic sedimentary characteristics in different geological periods, so there is a strong nonlinear mapping relationship between porosity and logging parameters. It is very important to make full use of logging parameters to predict the shale content and porosity of the reservoir for precise reservoir description. Deep neural network technology has strong data structure mining ability and has been applied to shale content prediction in recent years. In fact, the gated recurrent unit (GRU) neural network has further advantage in processing serialized data. Therefore, this study proposes a method to predict porosity by combining multiple logging parameters based on the GRU neural network. Firstly, the correlation measurement method based on Copula function is used to select the logging parameters most relevant to porosity parameters. Then, the GRU neural network is used to identify the nonlinear mapping relationship between logging data and porosity parameters. The application results in an exploration area of the Ordos basin show that this method is superior to multiple regression analysis and recurrent neural network method, which indicates that the GRU neural network is more effective in predicting a series of reservoir parameters such as porosity.