%0 Journal Article %T Application of Bayesian in determining productive zones by well log data in oil wells %+ School of Mining, Petroleum and Geophysics Engineering %+ Faculty of Geography %+ National Iranian Oil Company (NIOC) %A Masoudi, Pedram %A Tokhmechi, Behzad %A Ansari, Majid %A Jafari, Mohammad %A Zamanzadeh, Shahram %< avec comité de lecture %@ 0920-4105 %J Journal of Petroleum Science and Engineering %I Elsevier %V 94-95 %P 47-54 %8 2012 %D 2012 %R 10.1016/j.petrol.2012.06.028 %K net pay %K productive zone %K Bayesian Network %K petrophysics %K well test %Z Sciences of the Universe [physics]/Earth Sciences/Applied geologyJournal articles %X Exploration specialists conventionally utilize a cut-off-based method tofind productive zones inside the oil wells. Using conventional method, payzones are separated crisply from non-pay zones by applying cut-off values onsome petrophysical features.In this paper, a Bayesian technique is developed to find productivezones (net pays), and Bayesian Network is used to select the most appropriateinput features for this newly developed method. So, two Bayesian methodswere developed: the first one with conventional pay determination inputs(shale percent, porosity and water saturation), the other with two inputs,selected by Bayesian Network (porosity and water saturation). Twodeveloped Bayesian methods are applied on well log dataset of two wells:one well is dedicated for training and testing Bayesian methods, the other forchecking generalization ability of the proposed methods. Outputs of twopresented methods were compared with the results of conventional cut-offbasedmethod and production test results (i.e. a direct procedure to checkvalidation of proposed methods).Results show that the most prominent advantage of developedBayesian method is determination of net pays fuzzily with no need to identifycut-offs, in addition to higher precision of classification: nearly 30%improvement in precision of determining net pays of first well (training well),and about 50% improvement in precision of determining productive zonesthrough the generalizing well. %G English %2 https://insu.hal.science/insu-01382398/document %2 https://insu.hal.science/insu-01382398/file/Proof%20of%20Paper.pdf %L insu-01382398 %U https://insu.hal.science/insu-01382398 %~ INSU %~ GIP-BE