Student Seminar

Inversion of nuclear well-logging data using neural networks

Fri, 26 Feb 2016
Print
 
Student Seminar
 
Fafu Niu
Simon Fraser University
 
Inversion of nuclear well-logging data using neural networks
 
Feb 26, 2016
 

Synopsis

Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. This work looks at the application of neural networks in well-logging problems and specifically their utilization for inversion of nuclear downhole data. Simulated neutron and gamma-ray fluxes at a given detector location within a neutron logging tool were inverted to obtain formation properties such as porosity, salinity and oil/water saturation.The results show that neural networks could provide a reliable and fast prediction of these subsurface properties.