Towards understanding common features between natural and seismic images

Shafiq, Muhammad; Prabhushankar, Mohit; Di, Haibin; AlRegib, Ghassan

doi:10.1190/segam2018-2996501.1

Cited by 13 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al (2015) provides a review of some of the most commonly used techniques. More recently, unsupervised techniques based on deep learning models such as deep convolutional autoencoders have been explored (Qian et al, 2018;Shafiq et al, 2018;Veillard et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

A machine-learning benchmark for facies classification

et al. 2019

Self Cite

View full text Add to dashboard Cite

The recent interest in using deep learning for seismic interpretation tasks, such as facies classification, has been facing a significant obstacle, namely the absence of large publicly available annotated datasets for training and testing models. As a result, researchers have often resorted to annotating their own training and testing data. However, different researchers may annotate different classes, or use different train and test splits. In addition, it is common for papers that apply machine learning for facies classification to not contain quantitative results, and rather rely solely on visual inspection of the results. All of these practices have lead to subjective results and have greatly hindered the ability to compare different machine learning models against each other and understand the advantages and disadvantages of each approach. To address these issues, we open-source a fullyannotated 3D geological model of the Netherlands F3 Block. This model is based on the study of the 3D seismic data in addition to 26 well logs, and is grounded on the careful study of the geology of the region. Furthermore, we propose two baseline models for facies classification based on a deconvolution network architecture and make their codes publicly available. Finally, we propose a scheme for evaluating different models on this dataset, and we share the results of our baseline models. In addition to making the dataset and the code publicly available, this work helps advance research in this area by creating an objective benchmark for comparing the results of different machine learning approaches for facies classification.

show abstract

Section: Introductionmentioning

confidence: 99%

A machine-learning benchmark for facies classification

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results show that DCAE outperforms conventional methods like K-means or SOMs, Moreover, the results of DCAE are of much higher resolution and highlight important information. Reference [27] uses sparse autoencoder architecture that can detect major geological features from unlabeled seismic data. The model is tested on real and synthetic seismic data in order to extract relevant structures from the data.…”

Section: Related Workmentioning

confidence: 99%

Seismic Facies Segmentation Using Ensemble of Convolutional Neural Networks

Abid

Khan

Memon

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The use of machine learning for seismic interpretation is a growing area of interest for researchers. Manual interpretation demands time and specialized effort. The use of machine learning model will expedite the process. The Convolutional Neural Networks (CNNs) are a class of deep learning algorithms used for images. In this paper, seismic facies segmentation using encoder-decoder architecture of CNNs is proposed. The proposed method filled the gap using a multimodel approach for seismic interpretation. The novelty of the model is that it is not limited to the current dataset and semantic segmentation models. The encoder-decoder architecture input and output size is the same, and it allows the labelling of each pixel of the image. Four models are trained on the open-sourced F3 block Netherlands dataset. Images of 128 × 128 were extracted from the data. Data augmentation is used in two of the models to increase the data size for better model learning. Results of individual models and their ensemble are compared. Ensemble is performed by taking the average of the probabilities of the classes obtained from the trained models. Ensemble gave the superior results. Seven classes are segmented with a global pixel accuracy (GPA) of 98.52%, mean class accuracy (MCA) of 96.88%, and mean intersection over union (MIoU) of 93.92%.

show abstract

“…The scarcity of labeled data implies the unavailability of a validation set, which is a common problem in seismic image segmentation with limited samples. Previous studies [19] [23] [28] have also lacked a validation set for model selection during the training process. The absence of a validation set remains a concerning matter, despite the availability of various techniques to mitigate overfitting.…”

Section: Introductionmentioning

confidence: 99%

Seismic Stratigraphic Interpretation Based on Unsupervised Validation and Spectral Clustering Sampling

Luo,

Gu,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

With the continuous development of computer technology and significant improvements in computing power, deep learning has found increasing applications in seismic stratigraphy interpretation, showcasing notable advancements over traditional methods. However, due to the unique characteristics of seismic data, labeling such data has become extremely challenging and time-consuming, necessitating the involvement of professional geologists. Consequently, few-shot learning has garnered considerable attention for seismic image segmentation.Nevertheless, two key challenges remain in few-shot learning: selecting more representative samples and validating the model during training. As the availability of labeled samples decreases, we are left with inadequate data for the validation set. In this paper, instead of solely focusing on enhancing the network structure, we propose the utilization of Spectral Clustering Sampling (SCS) methods for training data selection. Additionally, we introduce a metric called Sum of Different (SD), which can be computed without the need for labeled data, to replace the conventional validation set loss employed in traditional validation approaches. Notably, By employing SCS methods for training data selection and introducing the SD metric to replace traditional validation set loss in F3 dataset, we have achieved remarkable outcomes.

show abstract

Towards understanding common features between natural and seismic images

Cited by 13 publications

References 18 publications

A machine-learning benchmark for facies classification

A machine-learning benchmark for facies classification

Seismic Facies Segmentation Using Ensemble of Convolutional Neural Networks

Seismic Stratigraphic Interpretation Based on Unsupervised Validation and Spectral Clustering Sampling

Contact Info

Product

Resources

About