With the expansion of machine learning algorithms, automatic lithology classification that uses well logging data is becoming significant in formation

Geophysical formation evaluation plays a fundamental role in hydrocarbon exploration and production processes. It is a process which describes different reservoir parameters using well field data. Porosity is one of the parameters that determines the amount of oil present in a rock formation and research in this area is mainly carried out by engineers and geoscientists in the petroleum industry. Accurate prediction of porosity is a difficult problem. This is mostly due to the failure in the understanding of spatial porosity parameter distribution. Artificial neural networks have proved to be a powerful tool for mapping complicated and non-linear relationships in petroleum studies. In this study, we analyze and compare generalized regression neural network (GRNN) and feed-forward back propagation neural network (FFBP) in modeling porosity in Zhenjing oilfield data. This study is calibrated on four wells of Zhenjing oilfield data. One well was used to find an empirical relationship between the well logs and porosity, while the other three wells were used to test the model’s predictive ability in the field, respectively. The findings proved that the GRN network can make more accurate and credible porosity parameter estimation than the commonly used FFBP network. Artificial intelligence can be exploited as a powerful instrument for predicting reservoir properties in geophysical formation evaluation and reservoir engineering in petroleum industry.

The Muli area is the only permafrost region on the Chinese mainland wherein gas hydrates have been discovered. The gas hydrates are present in the fractures and pore spaces of the host rocks with a lamellar or micro-disseminated structure. By combining conventional and image logs, we describe the thickness of the permafrost layer and the well log responses of the gas hydrate reservoir, and calculate the porosity and gas hydrate saturation. We then analyze the advantages and disadvantages of different logging methods for evaluating gas hydrate reservoirs. Our results indicate that (1) gas hydrates are present below the permafrost in the Muli area, (2) gas hydrates predominantly occur in rock fractures, (3) the apparent resistivity is sensitive to gas hydrates present in pore spaces, and both apparent resistivity and acoustic logs are sensitive to gas hydrates present in fractures, (4) a density log is more appropriate for calculating porosity, and (5) gas hydrate saturation can be effectively calculated by the Archie equation, the modified Archie equation, and the Indonesian equation.

Mudstone is very similar to shale except it lacks sheet bedding. Shale gas is widely concerned and successfully exploited commercially in the world, while gas-bearing mudstone is rarely paid attention. To evaluate the reservoir characteristics and exploitation potential of gas-bearing mudstone, a total of 127 mudstone samples from the Shanxi formation were tested by X-ray diffraction (XRD), scanning electron microscope (SEM), gas content, etc., and the qualitative identification and quantitative evaluation of gas-bearing mudstone reservoirs were performed on four wells using the logging curve overlay method and reservoir parameter calculation equations. The results showed that: (1) the average total gas content of core measurement is 1.81 m³/t, and the total content of brittle minerals is 44.2%, which confirms that mudstones can also have good gas content and fracturing performance; (2) logging evaluation the average thickness of gas-bearing mudstone is 55.7 m, the average total gas content is 1.6 m³/t, and the average brittleness index is 38.1%, which indicates that the mudstone of Shanxi formation in the study area is generally gas-bearing and widely distributed. All the results reveal that gas-bearing mudstone with block bedding has the same exploitation potential as shale with sheet bedding,which deserves more attention.