ISSN:
1365-246X
Source:
Blackwell Publishing Journal Backfiles 1879-2005
Topics:
Geosciences
Notes:
Artificial neural networks can learn relationships between sediment characteristics (burial depth, composition, coordinates and thickness of overlying Quaternary deposits) and overpressures from well data, after which they can interpolate and extrapolate to areas and depths not covered by wells. We analyse data from the south-eastern part of the Pannonian Basin. We use a neural network for analysing fluid overpressures because of the complex interaction of the key variables, making it difficult to derive the functional relationships required for a statistical analysis. The optimal topology of the network (number of hidden layers and neurons) is found by minimizing the network's training and testing errors. The optimal design of the network resembles the interactions scheme of the key variables.The Pannonian Basin, originally formed in an extensional regime, has been in a compressive state of stress since Late Pliocene, causing anomalous subsidence patterns. Numerical forward modelling of compaction-driven fluid overpressures shows that, due to an increase in the level of compressive interplate stress, the fluid overpressures in the deep subbasins have increased substantially since Late Pliocene, giving rise to a very high overpressure (up to 45 MPa) at present. The neural network analyses provide an independent estimate of the current amount of overpressuring in this basin, complementing the numerical forward modelling results. The overpressure profiles obtained by the two modelling approaches are in excellent agreement, showing the same magnitude of overpressures, a reversal of the overpressure in the deepest parts of the subbasins and a general decrease of the overpressure from SW to NE.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1111/j.1365-246X.1995.tb05731.x
Permalink