Search

The influence of karstification on gas reservoir formation is an area of interest in petroleum geology, and karst paleogeomorphology restoration is a topic of reservoir research. However, most previous studies of karst paleogeomorphology have focused on karst reservoirs, ignoring the influence of the karst paleogeomorphology on the overlying strata and gas accumulations. Therefore, the value of the petroleum geology information associated with karst paleogeomorphology is not maximized. The carbonate strata of the Leikoupo Formation were uplifted and exposed by the Indosinian movement, leading to the development of a weathered karst stratum (Lei 4 3 sub-member). Many commercial gas wells have been developed in the Lei 4 3 sub-member. Based on the latest drilling, logging, and two- and three-dimensional seismic data for the northwestern Sichuan Basin, we selected the residual thickness and the impression methods to restore the karst paleogeomorphology of the Lei 4 3 sub-member. The karst paleogeomorphology was generally high in the southeast and low in the northwest. The area can be successively divided into three secondary karst geomorphological units, namely, karst highlands, karst slopes, and karst depressions, and several tertiary geomorphological units. The karst geomorphology had the function of controlling reservoir, hydrocarbon source, and gas accumulation distribution. The karst processes were different in the various geomorphological units, further controlling the distribution and development of the karst reservoirs. The inherited geomorphology also controlled the sedimentation of the clastic rocks in the overlying formation. Due to the paleogeomorphological setting of higher in the east and lower in the west, the hydrocarbon generation intensity of the early Xujiahe Formation increases from the karst highland to the karst depression. Due to the cutting and lateral sealing of the formation by faults and karst valleys, there are no unified gas-water boundaries in the Lei 4 3 sub-member. As a result of the overall tectonic setting of high in the east and low in the west, the natural gas is enriched in the karst monadnocks. • Karst palaeogeomorphology at the top of the Leikoupo Formation was restored. • The karst geomorphology controlled the reservoir, source rocks and gas accumulation. • The gas accumulations have characteristics of each karst monadnock is a gas accumulation. [ABSTRACT FROM AUTHOR]

Assessment of production potential and prediction of sweet spots in unexploited shale gas wells are crucial technologies for achieving a high success rate in drilling. Most existing methods are only applicable for yield forecasting of shale gas wells with known geological and drilling/completion factors after production. In addition, the shale gas reservoir in the Longmaxi Formation in the southern Sichuan Basin of China is characterized by low porosity, low permeability, and diverse gas reservoir states. Thus, forecasting production from unexploited wells and predicting the exact location of the sweet spot under complex geological conditions have become challenging topic for both academia and industry. According to the first law of geography, shale gas wells that are closer in space have more similar geologic features. Based on this foundation, a machine-learning prediction model based on spatial correlation (SC-MLPM) is proposed for evaluating potential production of shale gas wells in the Changning play located in Longmaxi Formation in the southern Sichuan basin, China. Specifically, an improved K -nearest neighbor algorithm (SC-KNN) based on the spatial correlation characteristics of the exploited wells is designed to estimate the relevant geological factors of the unexploited wells in the same area. In addition, an extreme gradient lifting model based on Huber loss function (Hu-XGB) is developed to predict the potential production of unexploited shale gas wells, and then the shale gas sweet spot area in the research area is predicted quickly and accurately. The experimental results on 88 shale gas wells from Changning play show that the mean relative error of the prediction results of the proposed method is 9.8%. Furthermore, the results also determine that the sweet spots of shale gas wells in the research area are mainly developed in the northwest and northeast directions, and gradually become worse in the southeast direction. Eventually, experimental results for the Fox Creek play in Canada show that the proposed model obtains better predictive performance as the number of gas wells increases, and also verifies the generalizability. This work provides a basis for the efficient development of the research area. • A machine-learning prediction model based on spatial correlation is proposed. • An improved KNN algorithm is designed on the first law of geography. • An extreme gradient lifting model is developed to predict potential production. [ABSTRACT FROM AUTHOR]