arXiv subjects

Motaz Alfarraj

Publications and source records attributed to Motaz Alfarraj.

17 recordsLinked to original sources

arXiv2025

SeisCoDE: 3D Seismic Interpretation Foundation Model with Contrastive Self-Distillation Learning

Seismic interpretation is vital for understanding subsurface structures but remains labor-intensive, subjective, and computationally demanding. While deep learning (DL) offers promise, its success hinges on large, high-quality datasets, often scarce in geophysics. Foundation Models (FMs), which have shown significant success in fields like natural language processing and computer vision, offer a transformative opportunity for seismic interpretation by enabling knowledge transfer and generalization across interpretation tasks. However, the application of FMs in this domain remains limited, especially at the 3D scale, due to the absence of a domain-specific pretraining workflow. Here, our study sought to develop a pretraining strategy for 3D seismic interpretation by introducing a vision transformer-based Seismic Contrastive Self-Distillation Encoder (SeisCoDE), a novel self-supervised learning (SSL) framework that leverages seismic signal processing and attribute analysis, preserving seismic structural integrity during pretraining. By leveraging contrastive learning and self-distillation, SeisCoDE learns meaningful latent representations without the need for labeled data (zero-shot approach). Results indicate that SeisCoDE effectively captures critical seismic features and characteristics, producing robust latent feature representations that drive downstream seismic interpretation. It demonstrates enhanced generalization abilities across different seismic interpretation tasks, outperforming the conventional supervised learning UNet method. Overall, this research emphasizes the potential of FMs informed by seismic image processing and attribute analysis principles, paving the way for continued innovation integrating FMs for seismic interpretation, with the potential to revolutionize subsurface characterization and geophysical seismic exploration.

physics.geo-ph↗

arXiv2023

Recursions Are All You Need: Towards Efficient Deep Unfolding Networks

The use of deep unfolding networks in compressive sensing (CS) has seen wide success as they provide both simplicity and interpretability. However, since most deep unfolding networks are iterative, this incurs significant redundancies in the network. In this work, we propose a novel recursion-based framework to enhance the efficiency of deep unfolding models. First, recursions are used to effectively eliminate the redundancies in deep unfolding networks. Secondly, we randomize the number of recursions during training to decrease the overall training time. Finally, to effectively utilize the power of recursions, we introduce a learnable unit to modulate the features of the model based on both the total number of iterations and the current iteration index. To evaluate the proposed framework, we apply it to both ISTA-Net+ and COAST. Extensive testing shows that our proposed framework allows the network to cut down as much as 75% of its learnable parameters while mostly maintaining its performance, and at the same time, it cuts around 21% and 42% from the training time for ISTA-Net+ and COAST respectively. Moreover, when presented with a limited training dataset, the recursive models match or even outperform their respective non-recursive baseline. Codes and pretrained models are available at https://github.com/Rawwad-Alhejaili/Recursions-Are-All-You-Need .

cs.CV↗

arXiv2021

Meta-Optimization of Deep CNN for Image Denoising Using LSTM

The recent application of deep learning (DL) to various tasks has seen the performance of classical techniques surpassed by their DL-based counterparts. As a result, DL has equally seen application in the removal of noise from images. In particular, the use of deep feed-forward convolutional neural networks (DnCNNs) has been investigated for denoising. It utilizes advances in DL techniques such as deep architecture, residual learning, and batch normalization to achieve better denoising performance when compared with the other classical state-of-the-art denoising algorithms. However, its deep architecture resulted in a huge set of trainable parameters. Meta-optimization is a training approach of enabling algorithms to learn to train themselves by themselves. Training algorithms using meta-optimizers have been shown to enable algorithms to achieve better performance when compared to the classical gradient descent-based training approach. In this work, we investigate the application of the meta-optimization training approach to the DnCNN denoising algorithm to enhance its denoising capability. Our preliminary experiments on simpler algorithms reveal the prospects of utilizing the meta-optimization training approach towards the enhancement of the DnCNN denoising capability.

eess.IV↗

arXiv2021

Joint Learning for Spatial Context-based Seismic Inversion of Multiple Datasets for Improved Generalizability and Robustness

Seismic inversion plays a very useful role in detailed stratigraphic interpretation of seismic data. Seismic inversion enables estimation of rock properties over the complete seismic section. Traditional and machine learning-based seismic inversion workflows are limited to inverting each seismic trace independently of other traces to estimate impedance profiles, leading to lateral discontinuities in the presence of noise and large geological variations in the seismic data. In addition, machine learning-based approaches suffer the problem of overfitting if there is a small number of wells on which the model is trained. We propose a two-pronged strategy to overcome these problems. We present a Temporal Convolutional Network that models seismic traces temporally. We further inject spatial context for each trace into its estimations of the impedance profile. To counter the problem of limited labeled data, we also present a joint learning scheme whereby multiple datasets are simultaneously used for training, sharing beneficial information among each other. This results in the improvement in generalization performance on all datasets. We present a case study of acoustic impedance inversion using the open source SEAM and Marmousi 2 datasets. Our evaluations show that our proposed approach is able to perform robust and laterally consistent estimations of impedance in the presence of noisy seismic data and limited labels. We compare and contrast our approach to other learning-based seismic inversion methodologies in the literature. On SEAM, we are able to obtain an average MSE of 0.0966, the lowest among all other methodologies.

physics.geo-ph↗

arXiv2020

Spatiotemporal Modeling of Seismic Images for Acoustic Impedance Estimation

Seismic inversion refers to the process of estimating reservoir rock properties from seismic reflection data. Conventional and machine learning-based inversion workflows usually work in a trace-by-trace fashion on seismic data, utilizing little to no information from the spatial structure of seismic images. We propose a deep learning-based seismic inversion workflow that models each seismic trace not only temporally but also spatially. This utilizes information-relatedness in seismic traces in depth and spatial directions to make efficient rock property estimations. We empirically compare our proposed workflow with some other sequence modeling-based neural networks that model seismic data only temporally. Our results on the SEAM dataset demonstrate that, compared to the other architectures used in the study, the proposed workflow is able to achieve the best performance, with an average $r^{2}$ coefficient of 79.77\%.

eess.IV↗

arXiv2020

Fabric Surface Characterization: Assessment of Deep Learning-based Texture Representations Using a Challenging Dataset

Tactile sensing or fabric hand plays a critical role in an individual's decision to buy a certain fabric from the range of available fabrics for a desired application. Therefore, textile and clothing manufacturers have long been in search of an objective method for assessing fabric hand, which can then be used to engineer fabrics with a desired hand. Recognizing textures and materials in real-world images has played an important role in object recognition and scene understanding. In this paper, we explore how to computationally characterize apparent or latent properties (e.g., surface smoothness) of materials, i.e., computational material surface characterization, which moves a step further beyond material recognition. We formulate the problem as a very fine-grained texture classification problem, and study how deep learning-based texture representation techniques can help tackle the task. We introduce a new, large-scale challenging microscopic material surface dataset (CoMMonS), geared towards an automated fabric quality assessment mechanism in an intelligent manufacturing system. We then conduct a comprehensive evaluation of state-of-the-art deep learning-based methods for texture classification using CoMMonS. Additionally, we propose a multi-level texture encoding and representation network (MuLTER), which simultaneously leverages low- and high-level features to maintain both texture details and spatial information in the texture representation. Our results show that, in comparison with the state-of-the-art deep texture descriptors, MuLTER yields higher accuracy not only on our CoMMonS dataset for material characterization, but also on established datasets such as MINC-2500 and GTOS-mobile for material recognition.

eess.IV↗

arXiv2019

Semi-supervised Sequence Modeling for Elastic Impedance Inversion

Recent applications of machine learning algorithms in the seismic domain have shown great potential in different areas such as seismic inversion and interpretation. However, such algorithms rarely enforce geophysical constraints - the lack of which might lead to undesirable results. To overcome this issue, we have developed a semi-supervised sequence modeling framework based on recurrent neural networks for elastic impedance inversion from multi-angle seismic data. Specifically, seismic traces and elastic impedance (EI) traces are modeled as a time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for EI. The proposed workflow uses well-log data to guide the inversion. In addition, it uses seismic forward modeling to regularize the training and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target EI using 10 well logs for training on a synthetic data set.

physics.geo-ph↗

arXiv2019

Estimation of Acoustic Impedance from Seismic Data using Temporal Convolutional Network

In exploration seismology, seismic inversion refers to the process of inferring physical properties of the subsurface from seismic data. Knowledge of physical properties can prove helpful in identifying key structures in the subsurface for hydrocarbon exploration. In this work, we propose a workflow for predicting acoustic impedance (AI) from seismic data using a network architecture based on Temporal Convolutional Network by posing the problem as that of sequence modeling. The proposed workflow overcomes some of the problems that other network architectures usually face, like gradient vanishing in Recurrent Neural Networks, or overfitting in Convolutional Neural Networks. The proposed workflow was used to predict AI on Marmousi 2 dataset with an average $r^{2}$ coefficient of $91\%$ on a hold-out validation set.

eess.SP↗

arXiv2019

Semi-supervised Learning for Acoustic Impedance Inversion

Recent applications of deep learning in the seismic domain have shown great potential in different areas such as inversion and interpretation. Deep learning algorithms, in general, require tremendous amounts of labeled data to train properly. To overcome this issue, we propose a semi-supervised framework for acoustic impedance inversion based on convolutional and recurrent neural networks. Specifically, seismic traces and acoustic impedance traces are modeled as time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for acoustic impedance. The proposed workflow uses well log data to guide the inversion. In addition, it utilizes a learned seismic forward model to regularize the training and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target elastic impedance using 20 AI traces for training.

eess.IV↗

arXiv2019

Structure Label Prediction Using Similarity-Based Retrieval and Weakly-Supervised Label Mapping

Recently, there has been significant interest in various supervised machine learning techniques that can help reduce the time and effort consumed by manual interpretation workflows. However, most successful supervised machine learning algorithms require huge amounts of annotated training data. Obtaining these labels for large seismic volumes is a very time-consuming and laborious task. We address this problem by presenting a weakly-supervised approach for predicting the labels of various seismic structures. By having an interpreter select a very small number of exemplar images for every class of subsurface structures, we use a novel similarity-based retrieval technique to extract thousands of images that contain similar subsurface structures from the seismic volume. By assuming that similar images belong to the same class, we obtain thousands of image-level labels for these images; we validate this assumption in our results section. We then introduce a novel weakly-supervised algorithm for mapping these rough image-level labels into more accurate pixel-level labels that localize the different subsurface structures within the image. This approach dramatically simplifies the process of obtaining labeled data for training supervised machine learning algorithms on seismic interpretation tasks. Using our method we generate thousands of automatically-labeled images from the Netherlands Offshore F3 block with reasonably accurate pixel-level labels. We believe this work will allow for more advances in machine learning-enabled seismic interpretation.

eess.IV↗

arXiv2019

A Machine Learning Benchmark for Facies Classification

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 fully-annotated 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.

eess.IV↗

arXiv2019

Petrophysical Property Estimation from Seismic Data Using Recurrent Neural Networks

Reservoir characterization involves the estimation petrophysical properties from well-log data and seismic data. Estimating such properties is a challenging task due to the non-linearity and heterogeneity of the subsurface. Various attempts have been made to estimate petrophysical properties using machine learning techniques such as feed-forward neural networks and support vector regression (SVR). Recent advances in machine learning have shown promising results for recurrent neural networks (RNN) in modeling complex sequential data such as videos and speech signals. In this work, we propose an algorithm for property estimation from seismic data using recurrent neural networks. An applications of the proposed workflow to estimate density and p-wave impedance using seismic data shows promising results compared to feed-forward neural networks.

physics.geo-ph↗

arXiv2019

3D Curvature Analysis of Seismic Waveforms and its Interpretational Implications

The idea of curvature analysis has been widely used in subsurface structure interpretation from three-dimensional (3D) seismic data (e.g., fault/fracture detection and geomorphology delineation) by measuring the lateral changes in the geometry of seismic events. However, such geometric curvature utilizes only the kinematic information (two-way traveltime) of the available seismic signals. While analyzing the dynamic information (waveform), the traditional approaches (e.g., complex trace analysis) are often trace-wise and thereby fail to take into account the seismic reflector continuity and deviate from the true direction of geologic deposition, especially for steeply dipping formations. This study proposes extending the 3D curvature analysis to the waveforms in a seismic profile, here denoted as the waveform curvature, and investigates the associated implications for assisting seismic interpretation. Applications to the F3 seismic dataset over the Netherlands North Sea demonstrate the added values of the proposed waveform curvature analysis in four aspects. First, the capability of the curvature operator in differentiating convex and concave bending allows automatic decomposition of a seismic image by the reflector types (peaks, troughs and zero-crossings), which can greatly facilitate computer-aided horizon interpretation and modelling from 3D seismic data. Second, the signed minimum curvature offers a new analytical approach for estimating the fundamental and important reflector dip attribute by searching the orientation associated with least waveform variation. Third, the signed maximum curvature makes it possible to analyze the seismic signals along the normal direction of the reflection events. Finally, the curvature analysis promotes the frequency bands of the seismic signals and thereby enhances the apparent resolution on identifying and interpreting subtle seismic features.

physics.geo-ph↗

arXiv2019

Multiscale Fusion for Seismic Geometric Attribute Enhancement

In this abstract, we propose a multiscale fusion technique to enhance seismic geometric attributes, such as dip and curvature, which are very sensitive to noise present in seismic data. For a give seismic section, first, we construct a Gaussian pyramid that allows us to generate the seismic attribute at different resolutions (scales). Then, all attributes at the different scales are fused together to form the proposed multiscale enhanced attribute. Applications to the 3D seismic dataset over the Great South Basin in New Zealand demonstrate that the proposed method is capable of improving both the resolution and noise robustness of the first-order dip and the second-order curvature attributes, compared to existing methods and algorithm. Such improvement indicates the great potential of our multiscale fusion technique for enhancing the quality of more multitrace seismic attributes, such as coherence, flexure, and GLCM.

eess.IV↗

arXiv2019

Content-adaptive non-parametric texture similarity measure

In this paper, we introduce a non-parametric texture similarity measure based on the singular value decomposition of the curvelet coefficients followed by a content-based truncation of the singular values. This measure focuses on images with repeating structures and directional content such as those found in natural texture images. Such textural content is critical for image perception and its similarity plays a vital role in various computer vision applications. In this paper, we evaluate the effectiveness of the proposed measure using a retrieval experiment. The proposed measure outperforms the state-of-the-art texture similarity metrics on CURet and PerTEx texture databases, respectively.

eess.IV↗

arXiv2019

Multiresolution Analysis and Learning for Computational Seismic Interpretation

We explore the use of multiresolution analysis techniques as texture attributes for seismic image characterization, especially in representing subsurface structures in large migrated seismic data. Namely, we explore the Gaussian pyramid, the discrete wavelet transform, Gabor filters, and the curvelet transform. These techniques are examined in a seismic structure labeling case study on the Netherlands offshore F3 block. In seismic structure labeling, a seismic volume is automatically segmented and classified according to the underlying subsurface structure using texture attributes. Our results show that multiresolution attributes improved the labeling performance compared to using seismic amplitude alone. Moreover, directional multiresolution attributes, such as the curvelet transform, are more effective than the non-directional attributes in distinguishing different subsurface structures in large seismic datasets, and can greatly help the interpretation process.

eess.IV↗

arXiv2018

A comparative study of texture attributes for characterizing subsurface structures in seismic volumes

In this paper, we explore how to computationally characterize subsurface geological structures presented in seismic volumes using texture attributes. For this purpose, we conduct a comparative study of typical texture attributes presented in the image processing literature. We focus on spatial attributes in this study and examine them in a new application for seismic interpretation, i.e., seismic volume labeling. For this application, a data volume is automatically segmented into various structures, each assigned with its corresponding label. If the labels are assigned with reasonable accuracy, such volume labeling will help initiate an interpretation process in a more effective manner. Our investigation proves the feasibility of accomplishing this task using texture attributes. Through the study, we also identify advantages and disadvantages associated with each attribute.

cs.CV↗