2019
DOI: 10.3390/app9173553
|View full text |Cite
|
Sign up to set email alerts
|

A Stratigraphic Prediction Method Based on Machine Learning

Abstract: Simulation of a geostratigraphic unit is of vital importance for the study of geoinformatics, as well as geoengineering planning and design. A traditional method depends on the guidance of expert experience, which is subjective and limited, thereby making the effective evaluation of a stratum simulation quite impossible. To solve this problem, this study proposes a machine learning method for a geostratigraphic series simulation. On the basis of a recurrent neural network, a sequence model of the stratum type … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
8
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6
3
1

Relationship

1
9

Authors

Journals

citations
Cited by 33 publications
(8 citation statements)
references
References 31 publications
0
8
0
Order By: Relevance
“…Chang et al [20] subsequently identified lithofacies from core drilling data using the Kohonen self-organizing map (SoM) algorithm, which was demonstrated to provide higher prediction accuracy compared to the use of backpropagation neural networks (BPNNs) and standard SoM neural networks. Zhou et al [21] conducted geostratigraphic unit simulations based on a recursive neural network (RNN) to establish a stratigraphic sequence algorithm for predicting stratigraphic sequences from stratigraphic sequence models and stratigraphic thickness models as input. The work of de Lima et al [22] conducted lithofacies identification based on core image data processed using a deep convolutional neural network (CNN) trained with millions of core images.…”
Section: Introductionmentioning
confidence: 99%
“…Chang et al [20] subsequently identified lithofacies from core drilling data using the Kohonen self-organizing map (SoM) algorithm, which was demonstrated to provide higher prediction accuracy compared to the use of backpropagation neural networks (BPNNs) and standard SoM neural networks. Zhou et al [21] conducted geostratigraphic unit simulations based on a recursive neural network (RNN) to establish a stratigraphic sequence algorithm for predicting stratigraphic sequences from stratigraphic sequence models and stratigraphic thickness models as input. The work of de Lima et al [22] conducted lithofacies identification based on core image data processed using a deep convolutional neural network (CNN) trained with millions of core images.…”
Section: Introductionmentioning
confidence: 99%
“…Meanwhile, the red-bed soft rocks are rich in clay mineral (e.g., montmorillonite and kaolinite) which is sensitive to hydration-induced damage [4]. Hence, the special characteristics of red-bed soft rocks occasionally bring engineering disasters [5][6][7][8][9] (e.g., structure collapse in deep soft rock tunnel, slope slide, water infiltration induced deterioration, and creep induced large deformation problems). The study on deterioration mechanism is important to academic research and also the engineering guidance.…”
Section: Introductionmentioning
confidence: 99%
“…In subsurface reservoir applications, neural networks have become increasingly popular for representing complex non-linear functions particularly for lithofacies classification [13][14][15], seismic interpretation and inversion [16][17][18], and generating realisations that honour spatial observations in geostatistical models [19][20][21][22]. In geological modelling, neural networks have also been used for predicting stratigraphic units by interpreting borehole data as oriented spatial sequences or series of data that are processed using Recurrent Neural Networks (RNNs) [23]. By providing a parametrization for the direct generation of conditional realisations obtained using generative adversarial networks (GANs), [24] produced plausible realizations of binary channelized images while achieving dimensionality reduction of two orders of magnitude.…”
Section: Introductionmentioning
confidence: 99%