Lithofacies identi®cation using multiple adaptive resonance theory neural networks and group decision expert system

Lithofacies identi®cation supplies qualitative information about rocks. Lithofacies represent rock textures and are important components of hydrocarbon reservoir description. Traditional techniques of lithofacies identi®cation from core data are costly and di€erent geologists may provide di€erent interpretations. In this paper, we present a lowcost intelligent system consisting of three adaptive resonance theory neural networks and a rule-based expert system to consistently and objectively identify lithofacies from well-log data. The input data are altered into di€erent forms representing di€erent perspectives of observation of lithofacies. Each form of input is processed by a di€erent adaptive resonance theory neural network. Among these three adaptive resonance theory neural networks, one neural network processes the raw continuous data, another processes categorical data, and the third processes fuzzyset data. Outputs from these three networks are then combined by the expert system using fuzzy inference to determine to which facies the input data should be assigned. Rules are prioritized to emphasize the importance of ®ring order. This new approach combines the learning ability of neural networks, the adaptability of fuzzy logic, and the expertise of geologists to infer facies of the rocks. This approach is applied to the Appleton Field, an oil ®eld located in Escambia County, Alabama. The hybrid intelligence system predicts lithofacies identity from log data with 87.6% accuracy. This prediction is more accurate than those of single adaptive resonance theory networks, 79.3%, 68.0% and 66.0%, using raw, fuzzy-set, and categorical data, respectively, and by an errorbackpropagation neural network, 57.3%. 7 2000 Published by Elsevier Science Ltd. All rights reserved.