Título del libro: Society Of Exploration Geophysicists International Exposition And 83rd Annual Meeting, Seg 2013: Expanding Geophysical Frontiers
Título del capítulo: Permeability and porosity from integrated multiattributes and well log data using Smooth regression: Application to a south Florida aquifer
URSULA XIOMARA ITURRARAN VIVEROS;
Autores externos:
Idioma:
Inglés
Año de publicación:
2013
Palabras clave:
Aquifers; Hydrogeology; Mean square error; Mechanical permeability; Petroleum prospecting; Petroleum reservoir engineering; Porosity; Regression analysis; Seismic prospecting; Seismic response; Seismic waves; Artifical neural networks; Hydrocarbon reservoir; Mean Square Error (MSE); Neural network method; Permeability and porosities; Petrophysical properties; Seismic attributes; Surface seismic data; Well logging
Resumen:
Permeability and porosity estimations are essential to characterize both hydrocarbon reservoirs and aquifers. In most cases lateral variations of petrophysical properties cannot be deli-nated from aquired measurments at sparsely located wells. In this paper we integrate multiattributes from surface seismic data with well log permeability (k) and porosity () to produce permeabilty and porosity images for a carbonate aquifer in southestern Florida. We apply Smooth regression to select the best combination of seismic attributes by means of the Gamma test to aid in the construction of Artifical Neural Network models (ANN). This set of seismic attributes allows us to save time during the training of ANNs and sets a lower bound for Mean Square Errors (MSE), avoiding overfitting. We apply the trained ANNs to the seismic data to obtain interwell estimations for k and . We discuss and compare our results with those computed via linear regression. The Neural Network method successfully delineates a highly permeable zone that corresponds to a high water production in the aquifer. © 2013 SEG.
Entidades citadas de la UNAM:
ISBN:
9781629931883
Editorial:
Society of Exploration Geophysicists
