Path: Top > S1-Final Project > Geophysics Engineering-FTTM > 2008

EVALUASI PENERAPAN METODA INVERSI IMPEDANSI AKUSTIK DAN MULTIATRIBUT NEURAL NETWORK UNTUK PEMODELAN DISTRIBUSI CHANNEL DAN POROSITAS (STUDI KASUS : LAPANGAN BLACKFOOT ALBERTA CANADA)

Undergraduate Theses from JBPTITBPP / 2017-10-09 10:31:13
Oleh : NOVRIANTO PAMILWA CITAJAYA (NIM 12304009), S1 - Department of Geophysical Engineering
Dibuat : 2008, dengan 13 file

Keyword : multiatribute evaluation, seismis inversion method, acoustic impedance

Skripsi ini membahas evaluasi multiatribut dari data seismik atribut dan data log. Hasil yang telah di capai akan di bandingkan dengan hasil seismik inversi konvensional untuk memodelkan penyebaran channel dan distribusi porositas. Data yang digunakan adalah set data training daerah Blackfoot dari Hampson Russell Software Service. Metode multiatribut dalam penelitian ini dilakukan untuk memprediksi log porositas. Jumlah atribut yang digunakan di tentukan oleh proses step wise regression. Operator konvolusi digunakan untuk menyelesaikan masalah perbedaan frekuensi antara data seismik dan data log. Metode multiatribut yang linier transformasinya terdiri dari deret bobot yang diperoleh dari minimalisasi least square. Pada metoda non linier, Neural Network di gunakan dalam proses training dengan menggunakan atribut yang sudah ditentukan sebelumnya. Tiga tipe Neural Network yang dilakukan dalam studi ini adalah MLFN, PNN, dan RBF. PNN menjadi pilihan neural network utama karena mempunyai korelasi yang paling tinggi. Untuk mengetahui tingkat kepercayaan dari transformasi multi atribut dilakukan proses crossvalidasi. Dalam proses ini, setiap sumur secara sistematis tidak dipakai dalam proses training, dan transformasi diturunkan kembali dari well yang tersisa. Error validasi adalah rata-rata error dari semua well yang tidak digunakan. Error validasi mengukur error prediksi pada saat transformasi digunakan pada volume seismik. Metoda model based digunakan pada inversi seismik konvensional. Hasil yang diperoleh menunjukkan bahwa Metoda multiatribut Neural Network menghasilkan prediksi distribusi porositas pada top channel dan hasil seismik inversi AI dapat menggambarkan model distribusi channel.

Deskripsi Alternatif :

This thesis will discuss about multiattribute evaluation from seismic attribute and log property. The result will be compared with conventional seismic inversion method to modeling channel delineation and porosity prediction. Blackfoot training data set from Hampson Russell Software Service used for this study. Multiatrribute method used to predict porosity logs. The objective is to derive a multiattribute transform, which is a linear or nonlinear transform between a subset of the attributes and the target log values then we compare the result with conventional seismic inversion. The selected subset is determined by a process of forward stepwise regression, which derives increasingly larger subsets of attributes. An extension of conventional crossplotting involves the use of a convolutional operator to resolve frequency differences between the target logs and the seismic data. In the linear mode, the transform consists of a series of weights derived by least squares minimization. In the nonlinear mode, a neural network is trained, using the selected attributes as inputs. Three types of neural networks have been evaluated: the multilayer feedforward network (MLFN), probabilistic neural network (PNN) and Radial basis function (RBF). Because of its higher correlation, the PNN appears to be the network of choice. To estimate the reliability of the derived multiattribute transform, crossvalidation is used. In this process, each well is systematically removed from the training set, and the transform is rederived from the remaining wells. The prediction error for the hidden well is then calculated. The validation error, which is the average error for all hidden wells, is used as a measure of the likely prediction error when the transform is applied to the seismic volume. Model based method applied for conventional seismic inversion. Multi-attribute Neural Network result give distribution of porosity prediction on top channel. Acoustic impedance result give the model of channel distribution.

Copyrights : Copyright Â(c) 2001 by ITB Central Library. Verbatim copying and distribution of this entire article is permitted by author in any medium, provided this notice is preserved.

Beri Komentar ?#(0) | Bookmark

PropertiNilai Properti
ID PublisherJBPTITBPP
OrganisasiS
Nama KontakUPT Perpustakaan ITB
AlamatJl. Ganesha 10
KotaBandung
DaerahJawa Barat
NegaraIndonesia
Telepon62-22-2509118, 2500089
Fax62-22-2500089
E-mail Administratordigilib@lib.itb.ac.id
E-mail CKOinfo@lib.itb.ac.id