Seismic inversion is a process of predicting high-resolution stratigraphic parameters from low-resolution seismic data. Traditional methods tend to impose human prior knowledge, such as sparsity, the modeling process. Nowadays, with development deep learning, idea by learning data has gained great attention in varieties research fields. As data-driven method, an artificial neural network (ANN) already been explored many researchers field inversion. Compared ANN, convolutional (CNN) stronger...

Deep learning has achieved great success in a variety of research fields and industrial applications. However, when applied to seismic inversion, the shortage labeled data severely influences performance deep learning-based methods. In order tackle this problem, we propose novel impedance inversion method based on cycle-consistent generative adversarial network (Cycle-GAN). The proposed Cycle-GAN model includes two subnets discriminative subnets. Three kinds loss, including estimation are...

In exploration geophysics, the first arrivals on data acquired under complicated near-surface conditions are often characterized by significant static corrections, weak energy, low signal-to-noise ratio, and dramatic phase change, they difficult to pick accurately with traditional automatic procedures. We have approached this problem using a U-shaped fully convolutional network (U-net) first-arrival picking, which is formulated as binary segmentation problem. U-net has ability recognize...

Nowadays, convolutional neural network (CNN) has achieved great attention in varieties of research fields. Benefit from the strong learning ability CNN, knowledge contained labeled data set can be efficiently extracted. However, validity CNN is guaranteed by a sufficient number data. In field seismic impedance inversion, amount always limited. order to mitigate dependence on data, we propose solve inversion problem using 1D cycle-consistent generative adversarial (Cycle-GAN), which consists...

Abstract The elastic moduli of subsurface rocks saturated with geofluid often depend on the wave frequency and confining pressure due to wave‐induced fluid flow their significant intrinsic compressibility. Therefore, knowledge pressure‐dependent dispersion is usually used in broad practical scenarios such as discrimination situ abnormal detection. We propose a simple dual‐porosity model describe dependence fluid‐saturated rocks. First, we follow idea Shapiro yield more accurate formulas for...

Squirt flow, a phenomenon typically observed in porous cracked rocks, occurs due to the contrasting compressibility between pores and cracks, leading pore pressure diffusion dissipation of wave energy. Understanding influence structure on dispersion attenuation signatures squirt flow is essential for interpreting seismic sonic logging data various fields earth energy sciences, such as hydrocarbon exploration, geothermal exploitation, CO 2 sequestration. In this study, we construct simple...

It is hard to guarantee the strict synchronization of all jacking-up points in integral jacking a large-span continuous box girder bridge. This paper took Hengliaojing Bridge as background, which need up an object with 295m length and more than 10,000tons weight, adopted 3D software calculate unsynchronized working conditions, studied relationships between vertical difference girder's deformation behaviour. The aim verify maximum value difference, guide construction ensure safety. monitoring...

A rock permeated by tilted aligned fractures, which is common in the earth, can be considered as a transversely isotropic (TTI) medium under assumption of long wavelength. We develop feasible method to predict fracture parameters (namely weakness and dip angle) fluid type TTI using azimuthal seismic data. Based on an approximate stiffness matrix, we first deduce linear reflection coefficient gas-bearing terms new indicator parameters. The then rewritten form Fourier series decouple...

Seismic elastic parameter inversion translates seismic data into subsurface structures and physical properties of formations. Traditional model-based methods have limitations in retrieving complex geological structures. In recent years, deep learning emerged as preferable alternatives. Nevertheless, inverting multiple parameters using neural networks individually is computationally intensive can lead to overfitting due a shortage labeled field applications. Multi-task be employed invert...

The increasing penetration of distributed energy resources (DERs) in power systems has aroused interest economic dispatch (DED). While quadratic cost functions are usually adopted, those DERs not necessarily practice. Existing algorithms perform unsatisfying convergence rates under nonquadratic functions. Therefore, this article proposes a secant approximation-based method (SAM) for general convex to achieve efficient convergence. marginal represented by linear particular price intervals....

Quantitative prediction of reservoir properties (e.g., gas saturation, porosity, and shale content) tight reservoirs is great significance for resource evaluation well placements. However, the complex pore structures, poor connectivity, uneven fluid distribution sandstone make correlation between parameters elastic more complicated thus pose a major challenge in seismic characterization. We have developed partially connected double porosity model to calculate by considering structure...

Abstract Temperature and pressure variations during the geologic diagenesis process can lead to complex pore structures in tight rocks. The effective-medium theory, based on stress–strain relationship combination with structure parameters, be used describe elastic-wave responses of In this work, differential effective medium (DEM) self-consistent approximation (SCA) models are combined invert pore-crack spectrum. Voigt–Reuss–Hill average is estimate elastic moduli minerals. Then, SCA,...

Abstract Seismic impedance inversion is one of the key techniques for quantitative seismic interpretation. Most conventional post-stack approaches are based on linear theory, whereas relationship between response and highly nonlinear. Thus, it challenging to implement methods obtain high-resolution reservoir investigation. Convolutional neural network (CNN), a superior deep network, has strong learning ability, which can learn from data establish complex nonlinear mapping. However, CNN-based...

The task of seismic data interpretation is a time-consuming and uncertain process. Machine learning tools can help to build shortcut between raw reservoir characteristics interest. Recently, techniques involving convolutional neural networks have started gain momentum. Convolutional are particularly efficient at pattern recognition within images, this why they suitable for facies classification tasks. We experimented with three different architectures based on layers compared them synthetic...

With the increasing penetration of distributed energy resources (DERs) and their participation in electricity market, it becomes more desirable to apply algorithms for resource allocation order address resulting computational communicational challenges. Most existing solving network-constrained economic dispatch (NCED) problem require tuning certain auxiliary parameters. As a result, robustness these against varieties DERs is greatly undermined. In this paper, new algorithm, optimality...

Fracture networks are omnipresent in unconventional energy reservoirs. The inversion of fractures is vital importance to oil and gas exploration production. Most the existing methods developed based on homogeneous media theory rely a solitary physical descriptor. For instance, one commonly employed single property approach determination water saturation through use media's electrical conductivity. With fast development multi-physics geological survey, joint framework that suitable for...

With an increasing penetration of distributed energy resources (DERs) in Energy Internet, there is a surge interest economic dispatch (DED) problems. The existing literature mainly focuses on average consensus algorithms, the convergence which remains bottleneck practical applications. To improve rate DED, this paper proposes algorithm based optimized transition matrix (TM) Markov chain. A DED model firstly developed under consensus-based information exchange architecture, generator only...

Abstract Geofluid identification from seismic data are crucial for understanding reservoir characteristics. However, fluid indicators based on elastic parameter combinations show strong ambiguity in terms of geofluid identification. Although the effective pore-fluid bulk modulus proves to be superior indicator discrimination, it is limited empirical models such as critical porosity model. The consolidation model can evaluate and compaction sediments widely used due its better applicability....