Interpretation of Shallow Stratigraphic Facies Using a Self-Organizing Neural Network

Abstract

A study was recently conducted to assess the extent of hydrocarbon impacts to groundwater and soil resources at a regional petroleum refinery. To accomplish the study, 46 groundwater-monitoring wells were installed at the site. Data collected from the wells included detailed lithologic descriptions from samples and cuttings, and suites of geophysical well logs. Because the quality of the lithologic descriptions was erratic, our approach was to produce lithofacies interpretations based on gamma ray logs, used as input to a neural network classifier system.