Aplicação de redes neuronais artificiais ao tratamento e interpretação de perfis geofísicos de poço aberto

Abstract

The analysis of openhole wireline logs is of great importance for the subsurface mapping of geological layers and the identification and quantification of hydrocarbon and mineral deposits. An importants aspects are the determination of geological boundaries, the mineralogical identification and the well-to-well correlation, which can be a tedious and time-consuming task for the geologist. Automating this procedure is complicated but potentially rewarding because it may save the production geologist and log analyst substantial amounts of time. Artificial neural networks have been shown to handle this task efficiently including in cases where sequential algorithms have problems. We show in this thesis that neural networks can be used to determine layer boundaries, the mineralogical identification and the well-to-well correlation, on well logs, and we present the new networks archtectures. These procedures are tested on synthetic as well as actual field data.