arXiv subjects

Umair bin Waheed

Publications and source records attributed to Umair bin Waheed.

24 records · Page 2Linked to original sources

arXiv2021

Deep learning for low-magnitude earthquake detection on a multi-level sensor network

Automatic detection of low-magnitude earthquakes has become an increasingly important research topic in recent years due to a sharp increase in induced seismicity around the globe. The detection of low-magnitude seismic events is essential for microseismic monitoring of hydraulic fracturing, carbon capture and storage, and geothermal operations for hazard detection and mitigation. Moreover, the detection of micro-earthquakes is crucial to understand the underlying mechanisms of larger earthquakes. Various algorithms, including deep learning methods, have been proposed over the years to detect such low-magnitude events. However, there is still a need for improving the robustness of these methods in discriminating between local sources of noise and weak seismic events. In this study, we propose a convolutional neural network (CNN) to detect seismic events from shallow borehole stations in Groningen, the Netherlands. We train a CNN model to detect low-magnitude earthquakes, harnessing the multi-level sensor configuration of the G-network in Groningen. Each G-network station contains four geophones at depths of 50, 100, 150, and 200 meters. Unlike prior deep learning approaches that use 3-component seismic records only at a single sensor level, we use records from the entire borehole as one training example. This allows us to train the CNN model using moveout patterns of the energy traveling across the borehole sensors to discriminate between events originating in the subsurface and local noise arriving from the surface. We compare the prediction accuracy of our trained CNN model to that of the STA/LTA and template matching algorithms on a two-month continuous record. We demonstrate that the CNN model shows significantly better performance than STA/LTA and template matching in detecting new events missing from the catalog and minimizing false detections.

physics.geo-ph↗

arXiv2021

Deep-Learning Driven Noise Reduction for Reduced Flux Computed Tomography

Deep neural networks have received considerable attention in clinical imaging, particularly with respect to the reduction of radiation risk. Lowering the radiation dose by reducing the photon flux inevitably results in the degradation of the scanned image quality. Thus, researchers have sought to exploit deep convolutional neural networks (DCNNs) to map low-quality, low-dose images to higher-dose, higher-quality images thereby minimizing the associated radiation hazard. Conversely, computed tomography (CT) measurements of geomaterials are not limited by the radiation dose. In contrast to the human body, however, geomaterials may be comprised of high-density constituents causing increased attenuation of the X-Rays. Consequently, higher dosage images are required to obtain an acceptable scan quality. The problem of prolonged acquisition times is particularly severe for micro-CT based scanning technologies. Depending on the sample size and exposure time settings, a single scan may require several hours to complete. This is of particular concern if phenomena with an exponential temperature dependency are to be elucidated. A process may happen too fast to be adequately captured by CT scanning. To address the aforementioned issues, we apply DCNNs to improve the quality of rock CT images and reduce exposure times by more than 60\%, simultaneously. We highlight current results based on micro-CT derived datasets and apply transfer learning to improve DCNN results without increasing training time. The approach is applicable to any computed tomography technology. Furthermore, we contrast the performance of the DCNN trained by minimizing different loss functions such as mean squared error and structural similarity index.

eess.IV↗

arXiv2020

Solving the acoustic VTI wave equation using physics-informed neural networks

Frequency-domain wavefield solutions corresponding to the anisotropic acoustic wave equations can be used to describe the anisotropic nature of the earth. To solve a frequency-domain wave equation, we often need to invert the impedance matrix. This results in a dramatic increase in computational cost as the model size increases. It is even a bigger challenge for anisotropic media, where the impedance matrix is far more complex. To address this issue, we use the emerging paradigm of physics-informed neural networks (PINNs) to obtain wavefield solutions for an acoustic wave equation for transversely isotropic (TI) media with a vertical axis of symmetry (VTI). PINNs utilize the concept of automatic differentiation to calculate its partial derivatives. Thus, we use the wave equation as a loss function to train a neural network to provide functional solutions to form of the acoustic VTI wave equation. Instead of predicting the pressure wavefields directly, we solve for the scattered pressure wavefields to avoid dealing with the point source singularity. We use the spatial coordinates as input data to the network, which outputs the real and imaginary parts of the scattered wavefields and auxiliary function. After training a deep neural network (NN), we can evaluate the wavefield at any point in space instantly using this trained NN. We demonstrate these features on a simple anomaly model and a layered model. Additional tests on a modified 3D Overthrust model and a model with irregular topography also show the effectiveness of the proposed method.

physics.comp-ph↗

arXiv2020

Winning with Simple Learning Models: Detecting Earthquakes in Groningen, the Netherlands

Deep learning is fast emerging as a potential disruptive tool to tackle longstanding research problems across the sciences. Notwithstanding its success across disciplines, the recent trend of the overuse of deep learning is concerning to many machine learning practitioners. Recently, seismologists have also demonstrated the efficacy of deep learning algorithms in detecting low magnitude earthquakes. Here, we revisit the problem of seismic event detection but using a logistic regression model with feature extraction. We select well-discriminating features from a huge database of time-series operations collected from interdisciplinary time-series analysis methods. Using a simple learning model with only five trainable parameters, we detect several low-magnitude induced earthquakes from the Groningen gas field that are not present in the catalog. We note that the added advantage of simpler models is that the selected features add to our understanding of the noise and event classes present in the dataset. Since simpler models are easy to maintain, debug, understand, and train, through this study we underscore that it might be a dangerous pursuit to use deep learning without carefully weighing simpler alternatives.

cs.CV↗

arXiv2014

A comparison of high order explicit Runge-Kutta, extrapolation, and deferred correction methods in serial and parallel

We compare the three main types of high-order one-step initial value solvers: extrapolation, spectral deferred correction, and embedded Runge--Kutta pairs. We consider orders four through twelve, including both serial and parallel implementations. We cast extrapolation and deferred correction methods as fixed-order Runge--Kutta methods, providing a natural framework for the comparison. The stability and accuracy properties of the methods are analyzed by theoretical measures, and these are compared with the results of numerical tests. In serial, the 8th-order pair of Prince and Dormand (DOP8) is most efficient. But other high order methods can be more efficient than DOP8 when implemented in parallel. This is demonstrated by comparing a parallelized version of the well-known ODEX code with the (serial) DOP853 code. For an $N$-body problem with $N=400$, the experimental extrapolation code is as fast as the tuned Runge--Kutta pair at loose tolerances, and is up to two times as fast at tight tolerances.

math.NA↗

arXiv2013

Efficient traveltime solution of the acoustic TI eikonal equation

Numerical solutions of the eikonal (Hamilton-Jacobi) equation for transversely isotropic (TI) media are essential for imaging and traveltime tomography applications. Such solutions, however, suffer from the inherent higher-order nonlinearity of the TI eikonal equation, which requires solving a quartic polynomial for every grid point. Analytical solutions of the quartic polynomial yield numerically unstable formulations. Thus, we need to utilize a numerical root finding algorithm, adding significantly to the computational load. Using perturbation theory we approximate, in a first order discretized form, the TI eikonal equation with a series of simpler equations for the coefficients of a polynomial expansion of the eikonal solution, in terms of the anellipticity anisotropic parameter. Such perturbation, applied to the discretized form of the eikonal equation, does not impose any restrictions on the complexity of the perturbed parameter field. Therefore, it provides accurate traveltime solutions even for models with complex distribution of velocity and anisotropic anellipticity parameter, such as that for the complicated Marmousi model. The formulation allows for large cost reduction compared to using the exact TI eikonal solver. Furthermore, comparative tests with previously developed approximations illustrate remarkable gain in accuracy in the proposed algorithm, without any addition to the computational cost.

physics.geo-ph↗