Naslov
Using of neural network in porosity prediction (Beničanci field)

Autori
Malvić, Tomislav ; Prskalo, Smiljan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), stručni

Izvornik
XI. Congress of Hungarian Geomathematics (Rad je objavljen isključivo na "webu") / Geiger, Janos - Segedin : Hungarian Geological Society, Geomathematical Section of the Hungarian Geological Society, 2007

ISBN
Nema

Skup
XI. CONGRESS OF HUNGARIAN GEOMATHEMATICS

Mjesto i datum
Mórahalom, Mađarska, 10.05.2007. - 12.05.2007

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Domaća recenzija

Ključne riječi
Seismic attributes; neural network; porosity; Drava depression.

Sažetak
The Benicanci oil field, located in the eastern part of the Drava depression is still one of five main hydrocarbon reservoirs in Croatia. That makes very meaningful to plan and perform a whole new set of geological reinterpretations and improvements of field geological model. The application of the neural network approach in seismic attribute processing and finally reservoir porosity prediction is presented in the paper. The three seismic attributes were interpreted – amplitude, phase and frequencies making 3D seismic cube. This attributes were extrapolated at the 14 well locations, averaged and compared by the mean porosities. It made the network training. The network was of the backpropagation type. It was fitted through 10000 iterations, searching for the lowest value of correlation between attribute(s) and porosities and the minimal convergence. The best training was reached using all three attributes together, what indicated on tendency that neural networks like numerous inputs. Moreover, the previously interpolated porosity map was done using geostatistics, both Kriging and Cokriging approaches. The Cokriging approach, very interesting, included only reflection strength (derivation of amplitude) as secondary seismic source of information (compared by neural inputs of three attributes). It very clearly indicated on position of carefully and geologically meaningful selection of the network inputs for any reservoir analysis. Relatively smooth map, and rarely reaching of measured porosity minimum and maximum, strongly indicates on conclusion that neural estimation is more precisely than previously interpolations.

Izvorni jezik
Engleski

Znanstvena područja
Geologija

Napomena
Rad nije tiskan, već je isključivo objavljen na web stranicama kongresa. U planu je tiskanje istoga.

POVEZANOST RADA