Sediment classification using neural networks; an example from the Site-U1344A of IODP Expedition 323 in the Bering Sea

Online Access: Get full text
doi: 10.1016/j.dsr2.2013.03.024
Author(s): Ojha, Maheswar; Maiti, Saumen
Author Affiliation(s): Primary:
Council of Scientific and Industrial Research, National Geophysical Research Institute, Hyderabad, India
Other:
Indian Institute of Geomagnetism, India
Volume Title: Plio-Pleistocene paleoceanography of the Bering Sea
Volume Author(s): Takahashi, Kozo, editor; Ravelo, A. Christina; Okazaki, Yusuke
Source: Plio-Pleistocene paleoceanography of the Bering Sea, edited by Kozo Takahashi, A. Christina Ravelo and Yusuke Okazaki. Deep-Sea Research. Part II: Topical Studies in Oceanography, Vol.125-126, p.202-213. Publisher: Elsevier, Oxford, International. ISSN: 0967-0645
Note: In English. 37 refs.; illus., incl. 4 tables, sketch map
Summary: A novel approach based on the concept of Bayesian neural network (BNN) has been implemented for classifying sediment boundaries using downhole log data obtained during Integrated Ocean Drilling Program (IODP) Expedition 323 in the Bering Sea slope region. The Bayesian framework in conjunction with Markov Chain Monte Carlo (MCMC)/hybrid Monte Carlo (HMC) learning paradigm has been applied to constrain the lithology boundaries using density, density porosity, gamma ray, sonic P-wave velocity and electrical resistivity at the Hole U1344A. We have demonstrated the effectiveness of our supervised classification methodology by comparing our findings with a conventional neural network and a Bayesian neural network optimized by scaled conjugate gradient method (SCG), and tested the robustness of the algorithm in the presence of red noise in the data. The Bayesian results based on the HMC algorithm (BNN.HMC) resolve detailed finer structures at certain depths in addition to main lithology such as silty clay, diatom clayey silt and sandy silt. Our method also recovers the lithology information from a depth ranging between 615 and 655 m Wireline log Matched depth below Sea Floor of no core recovery zone. Our analyses demonstrate that the BNN based approach renders robust means for the classification of complex lithology successions at the Hole U1344A, which could be very useful for other studies and understanding the oceanic crustal inhomogeneity and structural discontinuities. Abstract Copyright (2016) Elsevier, B.V.
Year of Publication: 2016
Research Program: IODP Integrated Ocean Drilling Program
Key Words: 06 Petrology, Sedimentary; Bayesian analysis; Bering Sea; Classification; Cluster analysis; Cores; Expedition 323; IODP Site U1344; Integrated Ocean Drilling Program; Marine sediments; Monte Carlo analysis; Neural networks; North Pacific; Pacific Ocean; Principal components analysis; Regression analysis; Sediments; Statistical analysis
Coordinates: N590301 N590301 W1791212 W1791212
Record ID: 2017013138
Copyright Information: GeoRef, Copyright 2019 American Geosciences Institute. Reference includes data from CAPCAS, Elsevier Scientific Publishers, Amsterdam, Netherlands