A COMPARISON OF ARTIFICIAL NEURAL NETWORKS AND ORDINARY KRIGING DEPTH MAPS OF THE LOWER AND UPPER PANNONIAN STAGE BORDER IN THE BJELOVAR SUBDEPRESSION, NORTHERN CROATIA

Journal Title: UNKNOWN - Year 2016, Vol 31, Issue 3

Abstract

Computerised mapping of subsurface strata is possible with a wide range of methods and techniques, such as geostatistical interpolation and stochastic simulations, but also with geomathematical methods. Geomathematical methods are, for example, the use of statistics in geology and the use of artificial neural networks. Artificial neural networks are primarily used in the case of flawed data and data that is in a non-linear relation. The set hypothesis of successful mapping of depth data using this original artificial neural network algorithm is confirmed using statistical analysis and comparison with geostatistical interpolation methods. The algorithm is made in „R“, an open source statistical computing software, and is used on the mapping of depth of the e-log marker „Rs5“ in the Bjelovar Subdepression, Northern Croatia, that is the border between the Lower and Upper Pannonian stages in the Croatian part of the Pannonian Basin System. The neural network architecture that produced the best responses is a network with two hidden layers, with 10 and 6 neurons, respectively. A backpropagation algorithm is used. Two methods were compared by cross-validation and the neural network produced a mean squared error as 16294.5, and Ordinary Kriging produced 14638.35.

Authors and Affiliations

Marijan Šapina

Keywords

Related Articles

Svjetlosno onečišćenje grada Zagreba u periodu prosinac 2010. - srpanj 2011

Svjetlosno onečišćenje povećanje je prirodne vrijednosti osvjetljenja okoliša kao posljedica ljudskog djelovanja. U uvodu članka dajemo pregled uzroka i posljedica svjetlosnog onečišćenja te opisujemo tri osnovne metode...

POLUAUTOMATIZIRANI POSTUPAK IZRADE GEOLOŠKIH PROFILA

Paper presents semi-automated technique for creating geological profles. Technique is based on manual geological correlation, and on computer tools which ensure automation of the remaining part of procedure, namely fr...

PRELIMINARNI PRORAČUN POTENCIJALNOGA SKLADIŠTA NISKORADIOAKTIVNOGA I SREDNJORADIOAKTIVNOGA OTPADA

Problematika je gospodarenja radioaktivnim otpadom (RAO) u RH zbog izostanka sustavnoga rješavanja u stalnome rastu, pri čemu je u ovome radu težište stavljeno na skladištenje RAO-a, kao jedne od bitnih faza gospodarenja...

STUDIJA RASPODJELE U MODELU AKTIVACIJSKE ENERGIJE UPORABOM RAZLIČITIH FUNKCIJA RASPODJELE KOD PROBLEMA IZOTERMALNE PIROLIZE

Glavni cilj rada bio je usporedba rezultata dobivenih uporabom različitih vjerojatnosnih funkcija. Predviđen je model n-toga reda za model raspodjele aktivacijske energije (skr. MRAE), i to primjenom tehnike asimptotske...

MOGUĆNOST VODOOPSKRBE PODRUČJA USORE

U aluviju rijeke Usore razvijen je kvartarni šljunkoviti vodonosnik iz kojega je moguće pridobiti potrebite količine vode za vodoopskrbu područja Usore. To je plitki otvoreni vodonosnik visoke propusnosti. Debljina mu do...

Download PDF file
  • EP ID EP30122
  • DOI 10.17794/rgn.2016.3.6
  • Views 172
  • Downloads 3

How To Cite

Marijan Šapina (2016). A COMPARISON OF ARTIFICIAL NEURAL NETWORKS AND ORDINARY KRIGING DEPTH MAPS OF THE LOWER AND UPPER PANNONIAN STAGE BORDER IN THE BJELOVAR SUBDEPRESSION, NORTHERN CROATIA. UNKNOWN, 31(3), -. https://www.europub.co.uk/articles/-A-30122