相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Geochemistry & Geophysics
Kyubo Noh et al.
Summary: Deep learning techniques are used for geophysical seismic facies classification to avoid subjectivity. However, these algorithms are black boxes and lack interpretability. To address this issue, explainable deep learning methods have been developed and applied, using prototype-based neural networks to provide more interpretable results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Energy & Fuels
Quan Ren et al.
Summary: Lithology identification using geophysical log information is crucial for log interpretation and reservoir evaluation. However, the highly similar features and nonlinear characteristics of log curves pose challenges in the identification process. In this study, we propose an intelligent method combining principal component analysis and fuzzy decision tree to effectively address these issues. By introducing an adaptive fuzzy decision tree algorithm based on particle swarm optimization, the performance of the model is significantly improved. Experimental results demonstrate that the proposed model outperforms other identification models, achieving higher accuracy and improving overall performance.
GEOENERGY SCIENCE AND ENGINEERING
(2023)
Article
Geosciences, Multidisciplinary
David Lubo-Robles et al.
Summary: Mapping the lateral distribution and thickness of gas hydrates and associated free gas using seismic surveys is challenging. In this study, principal component analysis (PCA) was applied to select seismic attributes for self-organizing maps (SOM) to identify BSRs. Using a smaller subset of samples representing target seismic facies offers optimal BSR identification.
MARINE AND PETROLEUM GEOLOGY
(2023)
Article
Geochemistry & Geophysics
Harpreet Kaur et al.
Summary: This paper proposes a deep neural network-based framework for seismic facies classification, utilizing DeepLabv3+ and generative adversarial network for segmentation and mapping. By analyzing the predicted facies from multiple networks and considering uncertainty, the interpretation process is accelerated with reduced human intervention and individual biases, achieving accurate facies classification.
INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION
(2023)
Article
Geochemistry & Geophysics
Jiachun You et al.
Summary: Seismic facies analysis is crucial for basin-fill studies and oil and gas exploration. The use of convolutional neural networks (CNNs) for interpretation is popular, but they lack transparency. This study compared class activation map (CAM) techniques with the explainable tool SHAP, and found that SHAP had better visualization capabilities and identified the importance of seismic attributes. The refined CNN model based on SHAP features showed better performance in predicting seismic facies, demonstrating the effectiveness of the proposed strategy.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Xingye Liu et al.
Summary: In this paper, a novel deep classified autoencoder learning approach is proposed for lithofacies identification in high-dimensional and complex problems. The method utilizes sparse constraint and additional regularization terms to improve performance and accuracy. Experimental results on well data and seismic data demonstrate the promising potential of the proposed method.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Xintao Chai et al.
Summary: Recently, there has been considerable attention on intelligent data processing and interpretation based on deep learning in the geosciences. However, the lack of authoritative and representative open data for training and testing artificial neural networks (ANNs) poses a significant obstacle. In this study, the authors open source a package for deep learning-based seismic facies classification (SFC) using the Society of Exploration Geophysicists (SEG) 2020 Machine Learning (ML) Blind-Test Challenge Data. They enhance the performance of the network by incorporating residual connections and conduct benchmarking experiments to evaluate the framework. The results demonstrate the reliability and robustness of the proposed approach in predicting facies.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geosciences, Multidisciplinary
Soumi Chaki et al.
Summary: This paper proposes a framework based on Probabilistic Neural Network (PNN) for lithology classification using seismic attributes. The framework is compared with existing supervised classifiers in terms of performance measures such as classification accuracy, sensitivity, and specificity. The study also investigates the selection of appropriate parameters for the classifiers and the importance of individual seismic predictors. The framework is shown to be helpful in estimating the probability of hydrocarbon presence in a large study area.
JOURNAL OF APPLIED GEOPHYSICS
(2022)
Article
Geosciences, Multidisciplinary
Karelia La Marca et al.
Summary: The study utilizes unsupervised machine learning methods such as self-organizing maps to analyze seismic attributes and provide multi-attribute combinations for interpreting geological elements in deepwater environments, aiding in the understanding of features in the basin including channels, sediments, and shales. The results show that this method enhances the interpretation of geological features, helping to optimize drilling plans.
MARINE AND PETROLEUM GEOLOGY
(2022)
Article
Geochemistry & Geophysics
Runhai Feng et al.
Summary: This study introduces a method to predict lithofacies based on seismic data using convolutional neural networks in a Bayesian framework, and quantifies uncertainty in classification through variational methods. By drawing multiple random samples from the trained distribution to simulate an ensemble predictor, the method achieves lithofacies classification. Uncertainty assessment shows higher confidence in classification within internal regions.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Matthew Middlehurst et al.
Summary: HIVE-COTE is a heterogeneous meta ensemble algorithm for time series classification, which has been state of the art for accuracy on the UCR time series classification archive since it was first proposed in 2016. Recently upgraded to HIVE-COTE 2.0, it introduces two new classifiers and a rocket classifier ensemble, demonstrating significantly higher accuracy than the current state of the art on multiple datasets.
Article
Geochemistry & Geophysics
Xingye Liu et al.
Summary: This study introduces a deep autoencoder for facies classification from elastic attributes, incorporating both labelled and unlabelled data. A semi-supervised deep autoencoder is developed to improve classification accuracy and reduce uncertainty by considering the mean of intra-class and population facies. The new method outperforms conventional deep autoencoder in the evaluation on well and seismic data, demonstrating its feasibility and superiority in classification accuracy.
GEOPHYSICAL PROSPECTING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Matthew Middlehurst et al.
Summary: Using bag of words representations is a common approach to time series classification, with newer dictionary-based algorithms like TDE showing greater accuracy and scalability. By replacing BOSS with TDE in HIVE-COTE, significant improvements in accuracy can be achieved. The new version of HIVE-COTE outperforms current top classifiers on the UCR time series archive, marking a new state of the art in time series classification.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2020, PT I
(2021)
Article
Geochemistry & Geophysics
Dario Grana et al.
Article
Computer Science, Artificial Intelligence
Angus Dempster et al.
DATA MINING AND KNOWLEDGE DISCOVERY
(2020)
Article
Geochemistry & Geophysics
Mingliang Liu et al.
Article
Geochemistry & Geophysics
Pu Wang et al.
Article
Geochemistry & Geophysics
Xingye Liu et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Computer Science, Artificial Intelligence
James Large et al.
DATA MINING AND KNOWLEDGE DISCOVERY
(2019)
Article
Computer Science, Artificial Intelligence
Carl H. Lubba et al.
DATA MINING AND KNOWLEDGE DISCOVERY
(2019)
Article
Geochemistry & Geophysics
Dario Grana et al.
GEOPHYSICAL PROSPECTING
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Aaron Bostrom et al.
TRANSACTIONS ON LARGE-SCALE DATA- AND KNOWLEDGE-CENTERED SYSTEMS XXXII
(2017)
Article
Computer Science, Information Systems
Houtao Deng et al.
INFORMATION SCIENCES
(2013)
