Sedimentary Facies of the Longmaxi Formation Shale Gas Reservoir in the Weiyuan Area Based on Elemental Characteristics

The Lower Silurian Longmaxi Formation in the southern Sichuan Basin is composed of a series of dark carbonaceous shales deposited in a hydrostatic shelf reduction environment. In this study, the ratio of uranium to thorium (U/Th), the total organic carbon (TOC), and the biological silicon content (SiBio) were selected as the characteristic parameters to precisely analyze the sedimentary environment and its impact on reservoir quality. The results show that the Weiyuan area in the Early Silurian Longmaxi period experienced two transgression-regression cycles, forming two third-class sequences, SSQ1 and SSQ2, which can be divided into six sedimentary microfacies: organic-rich siliceous argillaceous shelf, organic-rich silicon-containing argillaceous shelf, organic-rich silty argillaceous shelf, deep-water silty argillaceous shelf, shallow-water silty argillaceous shelf, and shallow-water argillaceous silty shelf microfacies. The organic-rich siliceous argillaceous shelf and organic-rich silicon-containing argillaceous shelf microfacies developed in the deepest transgressive system tract (TST1), with high U/Th, high TOC, and high SiBio, which are identified as the main control facies for reservoir development. These two microfacies are located in the middle of the study area, while a transition occurs in the east affected by the Neijiang Uplift. According to the classification criteria proposed in this article, the favourable shale gas reservoirs in Weiyuan area are characterized with high U/Th (>1.25), high TOC (>3%), and high SiBio (>15%). This paper proposed an evaluation method for shale sedimentary facies based on elemental and electrical logging characteristics, avoiding the limitations of core samples, which makes the quantitative division of shale sediments and the efficient recognition of high-quality reservoirs available. It is of great significance for delineating the potential production areas in the study area and beneficial for the scaled development of shale gas reservoirs.

Optimized algorithm for multipoint geostatistical facies modeling based on a deep feedforward neural network

Reservoir facies modeling is an important way to express the sedimentary characteristics of the target area. Conventional deterministic modeling, target-based stochastic simulation, and two-point geostatistical stochastic modeling methods are difficult to characterize the complex sedimentary microfacies structure. Multi-point geostatistics (MPG) method can learn a priori geological model and can realize multi-point correlation simulation in space, while deep neural network can express nonlinear relationship well. This article comprehensively utilizes the advantages of the two to try to optimize the multi-point geostatistical reservoir facies modeling algorithm based on the Deep Forward Neural Network (DFNN). Through the optimization design of the multi-grid training data organization form and repeated simulation of grid nodes, the simulation results of diverse modeling algorithm parameters, data conditions and deposition types of sedimentary microfacies models were compared. The results show that by optimizing the organization of multi-grid training data and repeated simulation of nodes, it is easier to obtain a random simulation close to the real target, and the simulation of sedimentary microfacies of different scales and different sedimentary types can be performed.

Intelligent Identification Method of Sedimentary Microfacies Based on DMC-BiLSTM

Sedimentary microfacies division is the basis of oil and gas exploration research. The traditional sedimentary microfacies division mainly depends on human experience, which is greatly influenced by human factor and is low in efficiency. Although deep learning has its advantage in solving complex nonlinear problems, there is no effective deep learning method to solve sedimentary microfacies division so far. Therefore, this paper proposes a deep learning method based on DMC-BiLSTM for intelligent division of well-logging—sedimentary microfacies. First, the original curve is reconstructed multi-dimensionally by trend decomposition and median filtering, and spatio-temporal correlation clustering features are extracted from the reconstructed matrix by Kmeans. Then, taking reconstructed features, original curve features and clustering features as input, the prediction types of sedimentary microfacies at current depth are obtained based on BiLSTM. Experimental results show that this method can effectively classify sedimentary microfacies with its recognition efficiency reaching 96.84%.

Application of well-seismic reservoir prediction technology in oilfield

This study mainly takes the thick oil layer in Lamadian Oilfield as an example. This oil layer is mainly developed in the area dominated by fluvial sediments, and the reservoir sand body space changes frequently. If we only rely on the traditional single well logging data, it is difficult to directly and effectively predict the changes of the whole sedimentary sand body, and the spatial configuration relationship between river boundary and other sedimentary microfacies can not be effectively predicted. In order to effectively improve the understanding of cross-well sand bodies, it is necessary to effectively combine well seismic with reservoir prediction technology, give full play to the advantage of high resolution of well seismic in the longitudinal direction, and predict its specific adaptability and application according to different situations, so as to better improve the prediction accuracy of reservoir sand bodies and provide important information data for the rational adjustment of cross-well encryption and the formulation of effective measures to tap potential. Based on this, this article deeply analyzes the application value of well-seismic combined reservoir prediction technology in oil fields.