In recent years, Deep Neural Networks were successfully adopted in numerous domains to solve various image-related tasks, ranging from simple classification to fine borders annotation. Naturally, many researches proposed to use it to solve geological problems. Unfortunately, many of the seismic processing tools were developed years before the era of machine learning, including the most popular SEG-Y data format for storing seismic cubes. Its slow loading speed heavily hampers experimentation speed, which is essential for getting acceptable results. Worse yet, there is no widely-used format for storing surfaces inside the volume (for example, seismic horizons). To address these problems, we've developed an open-sourced Python framework with emphasis on working with neural networks, that provides convenient tools for (i) fast loading seismic cubes in multiple data formats and converting between them, (ii) generating crops of desired shape and augmenting them with various transformations, and (iii) pairing cube data with labeled horizons or other types of geobodies.
School of Earth and Planetary Sciences（地球与行星科学学院）；Curtin University（科廷大学）；Oil and Gas Innovation Centre（油气创新中心）
With the increased size and complexity of seismic surveys, manual labeling of seismic facies has become a significant challenge. Application of automatic methods for seismic facies interpretation could significantly reduce the manual labor and subjectivity of a particular interpreter present in conventional methods. A recently emerged group of methods is based on deep neural networks. These approaches are data-driven and require large labeled datasets for network training. We apply a deep convolutional autoencoder for unsupervised seismic facies classification, which does not require manually …
Imperial College London（帝国理工学院）；Open Energi Ltd.（Open Energi有限公司）；Technical University of Denmark（丹麦技术大学）；Euclidity SL（Euclidity SL公司）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；Expero Inc.（Expero公司）
Traditional physics-based approaches to infer sub-surface properties such as full-waveform inversion or reflectivity inversion are time-consuming and computationally expensive. We present a deep-learning technique that eliminates the need for these computationally complex methods by posing the problem as one of domain transfer. Our solution is based on a deep convolutional generative adversarial network and dramatically reduces computation time. Training based on two different types of synthetic data produced a neural network that generates realistic velocity models when applied to a real data…
Seismic horizons are geologically significant surfaces that can be used for building geology structure and stratigraphy models. However, horizon tracking in 3D seismic data is a time-consuming and challenging problem. Relief human from the tedious seismic interpretation is one of the hot research topics. We proposed a novel automatically seismic horizon tracking method by using a deep convolutional neural network. We employ a state-of-art end-to-end semantic segmentation method to track the seismic horizons automatically. Experiment result shows that our proposed neural network can automatical…
Reliable earthquake detection and seismic phase classification is often challenging especially in the circumstances of low magnitude events or poor signal-to-noise ratio. With improved seismometers and better global coverage, a sharp increase in the volume of recorded seismic data is witnessed. This makes the handling of the seismic data rather daunting based on traditional approaches and therefore fuels the need for a more robust and reliable method. In this study, we investigate two deep learningbased models, termed 1D ResidualNeuralNetwork (ResNet) and multi-branch ResNet, for tackling the …
Deep learning applications of seismic reservoir characterization often require generation of synthetic data to augment available sparse labeled data. An approach for generating synthetic training data consists of specifying probability distributions modeling prior geologic uncertainty on reservoir properties and forward modeling the seismic data. A prior falsification approach is critical to establish the consistency of the synthetic training data distribution with real seismic data. With the help of a real case study of facies classification with convolutional neural networks (CNNs) from an o…
We consider the reflection seismology problem of recovering the locations of interfaces and the amplitudes of reflection coefficients from seismic data, which are vital for estimating the subsurface structure. The reflectivity inversion problem is typically solved using greedy algorithms and iterative techniques. Sparse Bayesian learning framework, and more recently, deep learning techniques have shown the potential of data-driven approaches to solve the problem. In this paper, we propose a weighted minimax-concave penalty-regularized reflectivity inversion formulation and solve it through a m…
Data interpolation is a fundamental step in any seismic processing workflow. Among machine learning techniques recently proposed to solve data interpolation as an inverse problem, Deep Prior paradigm aims at employing a convolutional neural network to capture priors on the data in order to regularize the inversion. However, this technique lacks of reconstruction precision when interpolating highly decimated data due to the presence of aliasing. In this work, we propose to improve Deep Prior inversion by adding a directional Laplacian as regularization term to the problem. This regularizer driv…
Denoising and filtering are widely used in routine seismic-data-processing to improve the signal-to-noise ratio (SNR) of recorded signals and by doing so to improve subsequent analyses. In this paper we develop a new denoising/decomposition method, DeepDenoiser, based on a deep neural network. This network is able to learn simultaneously a sparse representation of data in the time-frequency domain and a non-linear function that maps this representation into masks that decompose input data into a signal of interest and noise (defined as any non-seismic signal). We show that DeepDenoiser achieve…
Enhancing the frequency bandwidth of the seismic data is always the pursuance at the geophysical community. High resolution of seismic data provides the key resource to extract detailed stratigraphic knowledge. Here, a novel approach, based on deep learning model, is introduced by extracting reflections from well log data to broaden spectrum bandwidth of seismic data through boosting low and high frequencies. The corresponding improvement is observed from the enhancement of resolution of seismic data as well as elimination of sidelobe artifacts from seismic wavelets. During the training stage …
Seismic velocity is one of the most important parameters used in seismic exploration. Accurate velocity models are key prerequisites for reverse-time migration and other high-resolution seismic imaging techniques. Such velocity information has traditionally been derived by tomography or full-waveform inversion (FWI), which are time consuming and computationally expensive, and they rely heavily on human interaction and quality control. We investigate a novel method based on the supervised deep fully convolutional neural network (FCN) for velocity-model building (VMB) directly from raw seismogra…
Seismic data processing heavily relies on the solution of physics-driven inverse problems. In the presence of unfavourable data acquisition conditions (e.g., regular or irregular coarse sampling of sources and/or receivers), the underlying inverse problem becomes very ill-posed and prior information is required to obtain a satisfactory solution. Sparsity-promoting inversion, coupled with fixed-basis sparsifying transforms, represent the go-to approach for many processing tasks due to its simplicity of implementation and proven successful application in a variety of acquisition scenarios. Lever…
In the past decade, deep learning algorithms gained a remarkable interest in the signal processing community. The availability of big datasets and advanced computational resources resulted in developing efficient algorithms. However, such algorithms are biased towards the training dataset. Thus, the transferability of deep-learning-based operators are challenging, especially when the goal is to apply the learned operator on a new dataset/domain. Lack of transferability of learned operator across domains hinders the applicability of deep learning algorithms in processing seismic data. Unlike ca…
I demonstrate that the conventional seismic full-waveform inversion algorithm can be constructed as a recurrent neural network and so implemented using deep learning software such as TensorFlow. Applying another deep learning concept, the Adam optimizer with minibatches of data, produces quicker convergence toward the true wave speed model on a 2D dataset than Stochastic Gradient Descent and than the L-BFGS-B optimizer with the cost function and gradient computed using the entire training dataset. I also show that the cost function gradient calculation using reverse-mode automatic differentiat…
In the context of a deep geological repository of high-level radioactive wastes, the French National Radioactive Waste Management Agency (Andra) has conducted an extensive characterization of the Callovo-Oxfordian argillaceous rock and surrounding formations in the Eastern Paris Basin. As part of this project, an accurate 3D seismic derived geological model is needed. The paper shows the procedure used for building the 3D seismic constrained geological model in depth by combining time-to-depth conversion of seismic horizons, consistent seismic velocity model and elastic impedance in time. It a…
Seismic phase association is a fundamental task in seismology that pertains to linking together phase detections on different sensors that originate from a common earthquake. It is widely employed to detect earthquakes on permanent and temporary seismic networks, and underlies most seismicity catalogs produced around the world. This task can be challenging because the number of sources is unknown, events frequently overlap in time, or can occur simultaneously in different parts of a network. We present PhaseLink, a framework based on recent advances in deep learning for grid-free earthquake ph…
An important step of seismic data processing is removing noise, including interference due to simultaneous and blended sources, from the recorded data. Traditional methods are time-consuming to apply as they often require manual choosing of parameters to obtain good results. We use deep learning, with a U-net model incorporating a ResNet architecture pretrained on ImageNet and further trained on synthetic seismic data, to perform this task. The method is applied to common offset gathers, with adjacent offset gathers of the gather being denoised provided as additional input channels. Here we sh…
In current seismic acquisition practice, there is an increasing drive for sparsely (in space) acquired data, often in irregular geometry. These surveys can trade off subsurface information for efficiency/cost - creating a problem of "missing seismic data" that can greatly hinder subsequent processing and interpretation. Reconstruction of regularly sampled dense data from highly sparse, irregular data can therefore aid in processing and interpretation of these far sparser, more efficient seismic surveys. Here, two methods are compared to solve the reconstruction problem in both space-time and w…
Recent work published by Lindsey et al find evidence for a deep and compact seismic source for the sunquake associated with the 2011 July 30 M9.3 flare, as well as seismic emission extending up to 10 mHz. We examine the sunquake independently, and a possible wavefront is found in the 8 mHz band, though no wavefront is easily discernible in the 10 mHz band. Additionally, we perform numerical simulations of seismic excitation modeled with the reported parameters and changes in the power spectra with increasing depth of the excitation source are examined. It is found that the peak frequency decre…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Machine learned tasks on seismic data are often trained sequentially and separately, even though they utilize the same features (i.e. geometrical) of the data. We present StorSeismic, as a framework for seismic data processing, which consists of neural network pre-training and fine-tuning procedures. We, specifically, utilize a neural network as a preprocessing model to store seismic data features of a particular dataset for any downstream tasks. After pre-training, the resulting model can be utilized later, through a fine-tuning procedure, to perform tasks using limited additional training. U…
Seismic imaging faces challenges due to the presence of several uncertainty sources. Uncertainties exist in data measurements, source positioning, and subsurface geophysical properties. Reverse time migration (RTM) is a high-resolution depth migration approach useful for extracting information such as reservoir localization and boundaries. RTM, however, is time-consuming and data-intensive as it requires computing twice the wave equation to generate and store an imaging condition. RTM, when embedded in an uncertainty quantification algorithm (like the Monte Carlo method), shows a many-fold inc…
East China University of Technology（东华理工大学）；Dalhousie University（达尔豪斯大学）；Stanford University（斯坦福大学）
Earthquake early warning systems are required to report earthquake locations and magnitudes as quickly as possible before the damaging S wave arrival to mitigate seismic hazards. Deep learning techniques provide potential for extracting earthquake source information from full seismic waveforms instead of seismic phase picks. We developed a novel deep learning earthquake early warning system that utilizes fully convolutional networks to simultaneously detect earthquakes and estimate their source parameters from continuous seismic waveform streams. The system determines earthquake location and m…
It is an extremely challenging task to precisely identify the reservoir characteristics directly from seismic data due to its inherit nature. Here, we successfully design a deep-learning model integrated with synthetic wedge models to overcome the geophysical limitation while performing the interpretation of thickness of sand bodies from a low resolution of seismic data. Through understanding and learning the geophysical relationship between seismic responses and corresponding indicators for sand thickness, the deep-learning model could automatically detect the locations of top and base of san…
Applying deep-learning models to geophysical applications has attracted special attentions during the past a couple of years. There are several papers published in this domain involving with different topics primarily focusing on synthetic data. Based on the presented results, reaching the satisfaction from geophysicists is largely far away the performance of the conventional algorithms. Moreover, it is extremely hard to find documents with detailed illustrations about what are the best practices that researchers should follow regarding how to design appropriate deep-learning models to effecti…
We present an application of deep generative models in the context of partial-differential equation (PDE) constrained inverse problems. We combine a generative adversarial network (GAN) representing an a priori model that creates subsurface geological structures and their petrophysical properties, with the numerical solution of the PDE governing the propagation of acoustic waves within the earth's interior. We perform Bayesian inversion using an approximate Metropolis-adjusted Langevin algorithm (MALA) to sample from the posterior given seismic observations. Gradients with respect to the model…
This paper introduces novel deep recurrent neural network architectures for Velocity Model Building (VMB), which is beyond what Araya-Polo et al 2018 pioneered with the Machine Learning-based seismic tomography built with convolutional non-recurrent neural network. Our investigation includes the utilization of basic recurrent neural network (RNN) cells, as well as Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) cells. Performance evaluation reveals that salt bodies are consistently predicted more accurately by GRU and LSTM-based architectures, as compared to non-recurrent architec…
As the number of seismic sensors grows, it is becoming increasingly difficult for analysts to pick seismic phases manually and comprehensively, yet such efforts are fundamental to earthquake monitoring. Despite years of improvements in automatic phase picking, it is difficult to match the performance of experienced analysts. A more subtle issue is that different seismic analysts may pick phases differently, which can introduce bias into earthquake locations. We present a deep-neural-network-based arrival-time picking method called "PhaseNet" that picks the arrival times of both P and S waves. …
Recently, there has been increasing interest in using deep learning techniques for various seismic interpretation tasks. However, unlike shallow machine learning models, deep learning models are often far more complex and can have hundreds of millions of free parameters. This not only means that large amounts of computational resources are needed to train these models, but more critically, they require vast amounts of labeled training data as well. In this work, we show how automatically-generated weak labels can be effectively used to overcome this problem and train powerful deep learning mod…
An Efficient Self-supervised Seismic Data Reconstruction Method Based on Self-Consistency Learning
The Key Laboratory of Earth Exploration & Information Techniques of Ministry Education（教育部地球探测与信息处理重点实验室）；School of Geophysics, Chengdu University of Technology（成都理工大学地球物理学院）；Chengdu University of Technology（成都理工大学）
To optimally monitor earthquake-generating processes, seismologists have sought to lower detection sensitivities ever since instrumental seismic networks were started about a century ago. Recently, it has become possible to search continuous waveform archives for replicas of previously recorded events (template matching), which has led to at least an order of magnitude increase in the number of detected earthquakes and greatly sharpened our view of geological structures. Earthquake catalogs produced in this fashion, however, are heavily biased in that they are completely blind to events for wh…
Danish Hydrocarbon Research and Technology Centre（丹麦油气研究与技术中心）；Technical University of Denmark（丹麦技术大学）；Institute of Petroleum Engineering（石油工程学院）；Heriot-Watt University（赫瑞-瓦特大学）；DHRTC（丹麦油气研究与技术中心）
Geoscience data often have to rely on strong priors in the face of uncertainty. Additionally, we often try to detect or model anomalous sparse data that can appear as an outlier in machine learning models. These are classic examples of imbalanced learning. Approaching these problems can benefit from including prior information from physics models or transforming data to a beneficial domain. We show an example of including physical information in the architecture of a neural network as prior information. We go on to present noise injection at training time to successfully transfer the network f…
Distributed Acoustic Sensing (DAS) is an emerging technology for earthquake monitoring and subsurface imaging. The recorded seismic signals by DAS have several distinct characteristics, such as unknown coupling effects, strong anthropogenic noise, and ultra-dense spatial sampling. These aspects differ from conventional seismic data recorded by seismic networks, making it challenging to utilize DAS at present for seismic monitoring. New data analysis algorithms are needed to extract useful information from DAS data. Previous studies on conventional seismic data demonstrated that deep learning m…
