Adaptive multi-resolution graph-based clustering algorithm for electrofacies analysis
- PDF / 9,417,331 Bytes
- 13 Pages / 595.22 x 842 pts (A4) Page_size
- 35 Downloads / 190 Views
Adaptive multi-resolution graph-based clustering algorithm for electrofacies analysis* Wu Hongliang1, Wang Chen3, Feng Zhou1, Yuan Ye1, Wang Hua-Feng2,3, and Xu Bin-Sen1 Abstract: Logging facies analysis is a significant aspect of reservoir description. In particular, as a commonly used method for logging facies identification, Multi-Resolution Graph-based Clustering (MRGC) can perform depth analysis on multidimensional logging curves to predict logging facies. However, this method is very time-consuming and highly dependent on the initial parameters in the propagation process, which limits the practical application effect of the method. In this paper, an Adaptive Multi-Resolution Graph-based Clustering (AMRGC) is proposed, which is capable of both improving the efficiency of calculation process and achieving a stable propagation result. More specifically, the proposed method, 1) presents a light kernel representative index (LKRI) algorithm which is proved to need less calculation resource than those kernel selection methods in the literature by exclusively considering those “free attractor” points; 2) builds a Multi-Layer Perceptron (MLP) network with back propagation algorithm (BP) so as to avoid the uncertain results brought by uncertain parameter initializations which often happened by only using the K nearest neighbors (KNN) method. Compared with those clustering methods often used in image-based sedimentary phase analysis, such as Self Organizing Map (SOM), Dynamic Clustering (DYN) and Ascendant Hierarchical Clustering (AHC), etc., the AMRGC performs much better without the prior knowledge of data structure. Eventually, the experimental results illustrate that the proposed method also outperformed the original MRGC method on the task of clustering and propagation prediction, with a higher efficiency and stability. Keywords: MRGC, AMRGC, MLP, logging facies analysis
Introduction Logging facies analysis is an important prerequisite for identifying reservoir sedimentary characteristics, and the automatic clustering method is usually required in the analysis process. However, due to the high feature dimensions extracted on the dataset, many clustering
algorithms are not well suited to practical situations, (i.e. log space is not equivalent to geological space, and two points that are close to each other in log space may not be similar geologically). At an earlier stage, Rogers proposed a BP neural network aiming at solving this problem point wisely, which requires few advanced statistical knowledge or strong log interpretation skills (Rogers, 1992). However, the BP neural network has
Manuscript received by the Editor September 28, 2019; revised manuscript received February 07, 2020. *This work was sponsored by the Science and Technology Project of CNPC (No. 2018D-5010-16 and 2019D- 3808) 1. Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China. 2. School of Computer Science and Technology, North China University of Technology, Beijing 100144, China. 3. College of Software, Bei
Data Loading...
