Estimation of absolute permeability using artificial neural networks (multilayer perceptrons) based on well logs and laboratory data from Silurian and Ordovician deposits in SE Poland

• DOI: 10.1007/s11600-019-00347-6
• Publication Date: 2019-09-04T19:03:29Z
• Authors: Sebastian Waszkie...; Paulina Krakowska...; Edyta Puskarczyk
• Keywords: Relative permeability

Permeability is a property of rocks which refers to the ability fluids flow through each substance. It depends on several factors as pore shape and diameter. Also presence type clay has large influence permeability value. can be measured rock sample in laboratory by injecting fluid under known condition, but this provides only point information. Due dependence parameter many factors, deterministic estimation based measurement well logs problematic. Many empirical methods for determining are available literature interpretation systems. An interesting approach problem use artificial neural networks modern, high-resolution logging tools. The authors decided MLP networks, allow used both test applied neighbouring wells. network was checked variants. Obtained results show legitimacy using issue estimating permeability. However, they also limitations resulting from lack accurate data or geological setting processes.