Neural network applications to reservoirs: Physics-based models and data models

摘要

Neural computations such as artificial neural networks (ANN) have aroused considerable interest over the last decades (e.g. Nikravesh et al, 2003; Graupe, 2007), and are being successfully applied across a wide range of problem areas, to domains as diverse as medicine, finance, engineering, geology and physics, to problems of complex dynamics and complex behavior prediction, classification or control. Several architectures, learning strategies and algorithms have been introduced into this highly dynamic field (e.g. Nikravesh et al., 2003; Sandham and Leggett, 2003; Aminzadeh and de Groot, 2006; Adeniran et al., 2010). Such new tools for the investigation of reservoirs are evaluated and tested during drilling processes and through logging analyses. This special volume is dedicated to the use of artificial intelligence in reservoir investigations, where physics-based models and data models are the core of the volume. Prediction of petrophysical parameters through various modern tools and technologies based on computational and analytical procedures (theory and applications) are also presented.