eprintid: 17463
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/74/63
datestamp: 2023-12-19 03:23:51
lastmod: 2023-12-19 03:23:51
status_changed: 2023-12-19 03:08:06
type: article
metadata_visibility: show
creators_name: Hossain, T.M.
creators_name: Hermana, M.
creators_name: Jaya, M.S.
creators_name: Sakai, H.
creators_name: Abdulkadir, S.J.
title: Uncertainty Quantification in Classifying Complex Geological Facies Using Bayesian Deep Learning
ispublished: pub
keywords: Bayesian networks; Deep learning; Geographical distribution; Geology; Inference engines; Inverse problems; Random processes; Seismic response; Stochastic models; Stochastic systems; Uncertainty analysis; Well logging, Bayes method; Bayesian; Bayesian deep learning; Deep learning; Facies classification; Modeling parameters; MonteCarlo methods; Seismic datas; Uncertainty; Uncertainty quantifications, Monte Carlo methods
note: cited By 1
abstract: Understanding geological differences in a proved reservoir requires precise facies classification. Predicting facies from seismic data is frequently seen as an inverse uncertainty quantification problem in seismic reservoir characterization. Typically, the uncertainty in the model parameters that regulate the geographic distributions is being ignored. The target facies and its uncertainty can be determined by calculating the posterior distribution of the model parameters conditioned on the seismic data under a Bayesian inference framework. It is believed that such facies classification model has a unique set of model parameters that best fits it. The proposed work is unique in that it quantifies the epistemic uncertainty of the predicted facies in blind well conditioned on Seismic Amplitude Versus Offset (AVO-Seismic) attributes in the Bayesian inference framework. Under this framework, parameter uncertainties of the neural net. weights and biases are calculated using their posterior distributions from the ensamble models generated by Marcov-Chains Monte-Carlo (MCMC) by assuming that the prior values of the weights and biases are uninformative. The proposed approach is also demonstrated on Synthetic Amplitude Versus Offset (AVO-Synthetic) dataset (derived from the well log information) and we have found high relevance in the predicted results. For comparision, a plain Deep Learning and Deep learning with Monte Carlo Dropout are employed and the results indicate that our model performs more efficiently comparing to the others indicating the possibility of the model to be used in real world solution to adequate facies classication. © 2013 IEEE.
date: 2022
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85141551238&doi=10.1109%2fACCESS.2022.3218331&partnerID=40&md5=d9204352c587e75cca36c69b95429885
id_number: 10.1109/ACCESS.2022.3218331
full_text_status: none
publication: IEEE Access
volume: 10
pagerange: 113767-113777
refereed: TRUE
issn: 21693536
citation:   Hossain, T.M. and Hermana, M. and Jaya, M.S. and Sakai, H. and Abdulkadir, S.J.  (2022) Uncertainty Quantification in Classifying Complex Geological Facies Using Bayesian Deep Learning.  IEEE Access, 10.  pp. 113767-113777.  ISSN 21693536