Intelligent Identification and Application of Low-Resistivity Thin Oil Layers of Dongying Formation in 35 Block of Chengbei
Li Hongrui;Han Changcheng;Yang Bin;Chen Yang;Lu Xinbian;Li Gan;Zhao Zhenyu;Munire;Chen Wanjun;Intelligent identification of low-resistivity thin oil layers is crucial for improving logging interpretation accuracy in complex reservoirs. In Dongying formation of Chengbei 35 block, Chengdao oilfield, the low-resistivity and thin interbed characteristics lead to ambiguous logging responses and minimal differences between productive and non-productive layers. This paper innovatively applies the Gradient Boosting Decision Tree(GBDT) model for intelligent identification of lowresistivity thin oil layers. By integrating logging curve characteristics, lithoelectric test results, production data, and reservoir physical properties, a logging feature set of low-resistivity layers is constructed through mathematical feature extraction. Key discrimination parameters are selected via a decision tree feature selection mechanism as input for the GBDT model, establishing an intelligent identification model for low-resistivity reservoirs. Combined with lithoelectric test data, the reservoir lower limit standards are determined. Application results show that the GBDT model achieves an identification accuracy of 89.5%, approximately 30% higher than the traditional logging numerical model, significantly reducing errors caused by manual interpretation and providing an intelligent solution for efficient exploration and development of low-resistivity thin oil layers.
Research on Intelligent Rock Color Recognition Method Based on Computer Vision
Tian Xiaoying;Zhang Zhaohui;Hao Bin;Li Zhiyong;Rapid standardization of rock color determination is a crucial aspect of geological research. Current methods primarily rely on expert visual description, Munsell color chart comparison, and spectral analysis, which fall short of meeting the demands for rapid and accurate rock color identification and digital standardization during extensive indoor and outdoor core observations. This paper proposes a computer vision-based intelligent rock color recognition method. Based on the Codes for names and colors of rocks in the petroleum geology(SY/T 5751—2012), a standard database containing 112 rock colors is constructed. Three algorithms—color thresholding, edge detection, and GrabCut—are designed to accurately segment target rock regions. Digital analysis, including color feature extraction, is performed on coordinate-based and gridded images to calculate the color vector of the rock image. Addressing the challenge of accurately identifying similar color systems, a weighted multi-feature fusion color matching algorithm is designed, incorporating evaluation indicators such as cosine similarity, Euclidean distance, RGB component differences, and brightness factor, significantly improving the system's ability to identify similar hues. A visualized intelligent rock color recognition system is developed using Python programming language and the PyQT6 framework, achieving digital quantitative identification of rock colors and improving recognition accuracy and efficiency. The results show that the system's identification results for 35 rock samples are highly consistent with the Munsell color chart interpretation results, with the consistency of hue(H), value(V), and chroma(C) reaching 91.43%, 85.71%, and 71.43%, respectively. The system also shows complete consistency in the identification of independent test samples, verifying the correctness of the core algorithm logic, and the average identification time can reach the millisecond level.
ST-Greedy-POD Reduced Basis Method for Parameterized Partial Differential Equations
Wang Li;Wang Zhaohong;Jiang Yaolin;Many engineering problems require simulations of parameterized partial differential equations. It takes a lot of time to solve this kind of problem when the discretization scale of the equation is larger and the parameter space is more complex. To improve the solving efficiency of partial differential equations with parameters, this paper proposes an ST-GreedyPOD reduced basis method for parameterized PDEs based on the space-time finite element discretization. Firstly, the parameterized PDE is discretized in both space and time via the space-time finite element method, yielding a parameterized algebraic equation. Then, the parameterized equation is separated into the parameter-dependent part and the parameterindependent part. Secondly, the Greedy algorithm is adopted to select optimal parameters from the parameter sample set according to posterior error, and the space-time reduced basis space is constructed iteratively, to further derive the space-time projection matrix. Finally, the parameterized system separated by parameters is projected onto the space-time reduced basis matrix to obtain the space-time parameterized reduced-order model and the corresponding reduced basis algorithm is presented. The proposed method reduces both the time variable and the space variable simultaneously. The results of two numerical examples verify the feasibility and effectiveness of the proposed method.
Dynamical Behavior of a Stochastic SVI Infectious Disease Model with Ornstein-Uhlenbeck Process
Cao Hong;Fan Xiaolin;Nie Linfei;Considering the great social benefits of vaccination and the unpredictability of changes in the natural environment, this paper introduces the Ornstein-Uhlenbeck process to characterize the stochastic fluctuations in the transmission rate,proposes and studies a stochastic SVI epidemic model. Firstly, the existence and uniqueness of the global positive solution for the model are analyzed. Secondly, by constructing appropriate Lyapunov functions, defining a compact set, and using tools such as Ito's formula, the existence of a stationary distribution for the model is proved. In addition, the sufficient condition for disease extinction is derived. Finally, some numerical simulations are used to explain the main theoretical results. The results show that, increasing vaccination rates can inhibit the rise in the number of infections and reduce the risk of transmission, but it can not completely eliminate the disease.
Sparse Canonical Correlation Analysis with L2,1-Norm for Functional Data
Zhang Zejiang;Yang Zhixia;Ye Junyou;Wang Yulan;Functional canonical correlation analysis is a key method in multivariate statistics for identifying optimal linear correlations between two functional datasets. However, some functions within these datasets may exhibit anomalies such as sudden changes or fluctuations that deviate from the overall trend, resulting to inaccurate results. To address this, we propose an improved method: Sparse functional canonical correlation analysis based on the L2,1-norm. This approach reduces outliers by optimizing the selection of orthogonal basis functions, thereby enhancing the accuracy and reliability of the analysis. Numerical experiments show that the L2,1-norm-based method significantly outperforms traditional methods.
Tracking the information about your manuscript
Communicate with the editorial office
Query manuscript payment status Edit officeCollecting, editing, reviewing and other affairs offices
Managing manuscripts
Managing author information and external review Expert Information Expert officeOnline Review
Online Communication with the Editorial Department
