Current methods in petroleum exploration generate a three dimensional view
of subsurface formations using surface geology, seismic surveys and well
logs. Well log data is used for vertical control in processing and
interpreting seismic data. Patterns in this data are also used for
characterizing and correlating geological formations Petrophysical
properties of subsurface formations and attributes of seismic data are
related to physical properties of the rocks and their contained fluids.
Acoustic impedance, Poisson’s ratio, bulk, shear and Young’s moduli have
been related to sonic and density logs. These logs are used to generate
synthetic seismograms which are correlated directly to seismic sections.
Using Neural Networks to relate seismic attributes to geophysical well logs
shows considerable promise. Additional research needs to be done to explore
all the possible relations and uses for Neural Networks in petroleum
exploration.