Repository logo

Browsing by Author "Opyrchał, Anna"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • thumbnail.journal.alt
    Item type:Article, Access status: Open Access ,
    Sztuczne sieci neuronowe dla uzupełnienia danych w geofizyce otworowej - wybrane przykłady
    (Wydawnictwa AGH, 2007) Jarzyna, Jadwiga A.; Opyrchał, Anna; Mozgowoj, Dariusz
    Artificial Neural Networks were used for reconstruction of well logs. Transit interval time recorded during acoustic log, bulk density as a result of gamma-gamma log and apparent resistivity were reconstructed on the basis of available logs. Perceptrons were chosen and the back propagation method was applied as the most effective training algorithm. Perceptrons with a few input neurons and at least a few neurons in a hidden layer turned out in reconstructing parameters. Basic statistics calculated for the reconstructed parameters compared to the measured or estimated ones acted as measures of correctness of solutions delivered by the networks. Intervals containing rocks of complex lithology and diversified stratigraphy turned out to be the most difficult to interpret. Results were applied in seismics, gravimetric and magnetotelluric interpretations.