Integration of adaptive neuro-fuzzy inference system, neural networks and geostatistical methods for fracture density modeling

Jafari, A ; Sharif University of Technology

857 Viewed
  1. Type of Document: Article
  2. DOI: 10.2516/ogst/2012055
  3. Abstract:
  4. Image logs provide useful information for fracture study in naturally fractured reservoir. Fracture dip, azimuth, aperture and fracture density can be obtained from image logs and have great importance in naturally fractured reservoir characterization. Imaging all fractured parts of hydrocarbon reservoirs and interpreting the results is expensive and time consuming. In this study, an improved method to make a quantitative correlation between fracture densities obtained from image logs and conventional well log data by integration of different artificial intelligence systems was proposed. The proposed method combines the results of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Neural Networks (NN) algorithms for overall estimation of fracture density from conventional well log data. A simple averaging method was used to obtain a better result by combining results of ANFIS and NN. The algorithm applied on other wells of the field to obtain fracture density. In order to model the fracture density in the reservoir, we used variography and sequential simulation algorithms like Sequential Indicator Simulation (SIS) and Truncated Gaussian Simulation (TGS). The overall algorithm applied to Asmari reservoir one of the SW Iranian oil fields. Histogram analysis applied to control the quality of the obtained models. Results of this study show that for higher number of fracture facies the TGS algorithm works better than SIS but in small number of fracture facies both algorithms provide approximately same results
  5. Keywords:
  6. Algorithms ; Artificial intelligence ; Fuzzy inference ; Fuzzy neural networks ; Fuzzy systems ; Inference engines ; Oil fields ; Petroleum reservoirs ; Quality control ; Tracking (position) ; Well logging ; Adaptive neuro-fuzzy inference system ; Artificial intelligence systems ; Geostatistical method ; Hydrocarbon reservoir ; Naturally fractured reservoirs ; Quantitative correlation ; Sequential indicator simulations ; Sequential simulation ; Fracture ; Algorithm ; Artificial neural network ; Fractured medium ; Fuzzy mathematics ; Geostatistics ; Modeling ; Oil field ; Reservoir characterization
  7. Source: Oil and Gas Science and Technology ; Vol. 69, issue. 7 , 2014 , pp. 1143-1154 ; ISSN: 12944475
  8. URL: http://ogst.ifpenergiesnouvelles.fr/articles/ogst/abs/2014/07/ogst110210/ogst110210.html