Application of Neural Networks in Petroleum Reservoir Lithology and Saturation Prediction¸

• Main Authors: Marko Cvetković, Josipa Velić, Tomislav Malvić
• Format: Article
• Language: English
• Published: Croatian Geological Survey 2009-06-01
• Series: Geologia Croatica
• Subjects: Kloštar field, neural network, prediction, sandstone, hydrocarbon saturation, Croatia
• Online Access: http://www.geologia-croatica.hr/ojs/index.php/GC/article/view/55

<p class="MsoNormal" style="margin: 0cm 0cm 0pt; mso-layout-grid-align: none;"><span style="font-family: Times New Roman;"><span style="font-size: 9pt; color: #231f20; font-family: TimesNewRomanPSMT; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: TimesNewRomanPSMT;">The Klo</span><span style="font-size: 9pt; color: #231f20; mso-fareast-font-family: TimesNewRomanPSMT; mso-bidi-font-family: TimesNewRomanPSMT; mso-ascii-font-family: TimesNewRomanPSMT;">&scaron;</span><span style="font-size: 9pt; color: #231f20; font-family: TimesNewRomanPSMT; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: TimesNewRomanPSMT;">tar oil field is situated in the northern part of the Sava Depression within the Croatian part of the Pannonian Basin. The major petroleum reserves are confi ned to Miocene sandstones that comprise two production units: the Lower Pontian I sandstone series and the Upper Pannonian II sandstone series. We used well logs from two wells through these sandstones as input data in the neural network analysis, and used spontaneous potential and resistivity logs (</span><em><span style="font-size: 9pt; color: #231f20; font-family: TimesNewRomanPS-ItalicMT; mso-fareast-font-family: TimesNewRomanPSMT; mso-bidi-font-family: TimesNewRomanPS-ItalicMT;">R</span></em><span style="font-size: 5pt; color: #231f20; font-family: TimesNewRomanPSMT; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: TimesNewRomanPSMT;">16 </span><span style="font-size: 9pt; color: #231f20; font-family: TimesNewRomanPSMT; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: TimesNewRomanPSMT;">and </span><em><span style="font-size: 9pt; color: #231f20; font-family: TimesNewRomanPS-ItalicMT; mso-fareast-font-family: TimesNewRomanPSMT; mso-bidi-font-family: TimesNewRomanPS-ItalicMT;">R</span></em><span style="font-size: 5pt; color: #231f20; font-family: TimesNewRomanPSMT; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: TimesNewRomanPSMT;">64</span><span style="font-size: 9pt; color: #231f20; font-family: TimesNewRomanPSMT; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: TimesNewRomanPSMT;">) as the input in network training. The fi rst analysis included prediction of lithology, which was defined as either sandstone or marl. These two rock types were assigned categorical values of 1 or 0 which were then used in numerical analysis. The neural network was also used to predict hydrocarbon saturation in selected wells. The input dataset was extended to depth and categorical lithology. The prediction results were excellent, because the training and prediction dataset showed little disagreement between the true and predicted values. At present, this study represents the best and most useful application of neural networks in the Croatian part of the Pannonian Basin.</span></span></p>