- https://ghassanalregib.com/
Ghassan AlRegib
Georgia Institute of Technology, College of Engineering, Faculty Member
Seismic inversion plays a very useful role in the detailed stratigraphic interpretation of migrated seismic volumes by enabling the estimation of reservoir properties over the complete volume. Traditional and machine learning-based... more
Seismic inversion plays a very useful role in the detailed stratigraphic interpretation of migrated seismic volumes by enabling the estimation of reservoir properties over the complete volume. 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 geologic variations in the seismic data. In addition, machine learning-based approaches suffer the problem of overfitting if there is only a small number of wells on which the model is trained. We have developed a two-pronged strategy to overcome these problems. We present a temporal convolutional network that models seismic traces temporally. We further inject the 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 data sets ...
Research Interests:
In this paper, implementation and outcomes of an undergraduate research course are presented. The associated gains and learning outcomes of the course are evaluated and benchmarked with other international undergraduate research... more
In this paper, implementation and outcomes of an undergraduate research course are presented. The associated gains and learning outcomes of the course are evaluated and benchmarked with other international undergraduate research experiences. The course was offered to undergraduate students at King Fahd University of Petroleum and Minerals (KFUPM). The research group structure adopts Georgia Tech model. The paper summarizes the course structure, content, and best practices. In addition, the results of undergraduate research experience survey are presented and analyzed. The students reported significant gains in understanding of the research process and significant improvements in writing and oral presentation skills.
Research Interests:
Research Interests:
Recognizing and tracking weak reflections, which are characterized by low amplitude, low signal-to-noise ratio, and low degree of lateral continuity, is a long-time issue in 3D seismic interpretation and reservoir characterization. The... more
Recognizing and tracking weak reflections, which are characterized by low amplitude, low signal-to-noise ratio, and low degree of lateral continuity, is a long-time issue in 3D seismic interpretation and reservoir characterization. The problem is particularly acute with unconventional, fractured shale reservoirs, in which the impedance contrast is low and/or reservoir beds are below the tuning thickness. To improve the performance of interpreting weak reflections associated with shale reservoirs, we have developed a new workflow for weak-reflection tracking guided by a robust structural-orientation vector (SOV) estimation algorithm. The new SOV-guided auto-tracking workflow first uses the reflection orientation at the seed location as a constraint to project the most-likely locations in the neighboring traces, and then locally adjust them to maximally match the target reflection. We verify our workflow through application to a test seismic data set that is typical of routine 3D seis...
Research Interests:
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 data sets for training and... more
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 data sets 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 led to subjective results and have greatly hindered our 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 geologic model of the Netherlands F3 block. This model is based on study of the...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this paper, we consider distributed estimation in energy-limited wireless sensor networks from lifetime-distortion perspective, where the goal is to maximize the network lifetime for a given distortion requirement. To take into account... more
In this paper, we consider distributed estimation in energy-limited wireless sensor networks from lifetime-distortion perspective, where the goal is to maximize the network lifetime for a given distortion requirement. To take into account both local quantization and multi-hop transmission, which are essential to save transmission energy and thus prolong the network lifetime, the network lifetime maximization problem is formulated as
Research Interests:
Research Interests:
Research Interests: Remote Sensing, Signal Processing, Distributed Algorithms, Multidisciplinary, Mean square error, and 15 moreSensor Network, Maximum Likelihood Estimation, Implementation, Energy Use, Energy Budget, Signal Detection, Lower Bound, Sensor Array, Information Rate, Active Sensor, Performance Bounds, Quadrature Amplitude Modulation, Distributed Algorithm, Distributed Estimation, and Deterministic Approach
Research Interests:
In this paper, we first explain the formulation of the trajectory triangulation: 3D reconstruction of a moving point from a series of 2D projections. The system has to be overconstrained to be solved by least squares techniques. We take... more
In this paper, we first explain the formulation of the trajectory triangulation: 3D reconstruction of a moving point from a series of 2D projections. The system has to be overconstrained to be solved by least squares techniques. We take advantage of the sparseness of real-world motions in the transformed domain, and borrow the concept of compressive sampling to reformulate the
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The identification of salt-dome boundaries in migrated seismic data volumes is important for locating petroleum reservoirs. The presence of noise in the data makes computer-aided salt-dome interpretation even more challenging. We have... more
The identification of salt-dome boundaries in migrated seismic data volumes is important for locating petroleum reservoirs. The presence of noise in the data makes computer-aided salt-dome interpretation even more challenging. We have developed noise-robust algorithms that could label boundaries of salt domes effectively and efficiently. Our research is twofold. First, we used a texture-based gradient to accomplish salt-dome detection. We found that by using a dissimilarity measure based on the 2D discrete Fourier transform, the algorithm was capable of efficiently detecting salt-dome boundaries with accuracy. At the same time, our analysis determined that the proposed algorithm was robust to noise. Once the detection is performed for an initial 2D seismic section, we track the initial boundaries through the data volume to accomplish an efficient labeling process by avoiding the parameter tuning that would have been necessary if detection had been performed for every seismic section...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Set Theory, Image Processing, Signal Processing, Data Compression, Video Compression, and 11 moreSpace Technology, Motion estimation, Sensor networks, Sensor Network, Decoding, Sensor Networks, Extrapolation, Intelligent Sensors, Video Encoder, Codecs, and Set Partitioning in Hierarchical Trees (SPIHT)
Whether interacting with a collaborative virtual environment, or CVE, locally or one networked across the Internet, any delay in the system can lead to a reduced sense of immersion. Input sensor delay and network delay are two common... more
Whether interacting with a collaborative virtual environment, or CVE, locally or one networked across the Internet, any delay in the system can lead to a reduced sense of immersion. Input sensor delay and network delay are two common problems in CVE design that can be overcome with the application of prediction algorithms to the system. The purpose of this experiment was to assess the quality of feed forward back propagation neural networks in predicting natural avatar arm movement typically used in a CVE. In addition the experiment attempts to find the bounds for precise neural network prediction. The results show many different combinations of back propagation neural network topologies are capable of predicting up to 400 ms of human arm movements relatively accurately.
Research Interests:
EVALUATION OF SELECTIVE ENCRYPTION TECHNIQUES FOR SECURE TRANSMISSION OF MPEG-COMPRESSED BIT ... the Data Encryption Standard (DES) or the RSA encryption algorithm ... bit-streams are typically huge and the encryptioddecryption algorithms... more
EVALUATION OF SELECTIVE ENCRYPTION TECHNIQUES FOR SECURE TRANSMISSION OF MPEG-COMPRESSED BIT ... the Data Encryption Standard (DES) or the RSA encryption algorithm ... bit-streams are typically huge and the encryptioddecryption algorithms are relatively ...
Research Interests:
... However, visual evaluation of the decoded video encrypted by this method reveals a lot ... 64% savings achieved by applying the same method, but without alternative encryption [6]. Extending ... I] B. Schneier, Applied Cvptography,... more
... However, visual evaluation of the decoded video encrypted by this method reveals a lot ... 64% savings achieved by applying the same method, but without alternative encryption [6]. Extending ... I] B. Schneier, Applied Cvptography, Second Edition, Protocols, Algorithms and Source ...