... environments require being able to anticipate operational issues and to plan contingencies for them. In most cases, seismic images are the only information available so drilling decisions must be made based on certain interpretations derived from them. However, seismic data contains uncertainties arising from...

... geophysicist 10 well logging geophysics building subsurface model subsurface model upstream oil & gas interpolation stratigraphic feature workflow seismic image Building subsurface models with horizon-guided interpolation and deep learning: applied to the Volve eld Shangsheng Yan1, Xiaoming...

...-lapse image co 2 applied geoscience plume nn prediction reservoir characterization upstream oil & gas time-lapse dataset fault segmentation environmental engineering seismic image neural network-based co interpretation baseline interpretation chadwick national university probability...

... We present a workflow to automate the channel interpretation in seismic images by using a 3D CNN (convolutional neural network). The main problem in applying the CNN to the channel interpretation is the inaccessibility of labeled training data. To settle this problem, we propose a workflow...

... We present a study on applying a machine learning (ML) technique to distinguish salt and non-salt voxels in 3D seismic images. The ML method we used is U-Net, which is a deep convolutional neural network. Specifically, our input data is a 3D seismic volume, and the output is a volume...

...:50 PM Presentation Time: 2:15 PM Location: 362A Presentation Type: Oral reservoir characterization initial model geometry new acquisition upstream oil & gas the overburden exploration geophysicist 10 seismic image modeling experiment suez velocity model gulf modeling study...

... We find that a sparse-pulse decomposition of seismic images provides accurate means to estimate the seismic source waveform. The corresponding spectral character allows us to estimate the quality factor Q to quantify seismic attenuation using the spectral ratio method. Tests on seismic trace...

... exploration geophysicist 10 seismic image das reliability geophone seg international exposition cnn The Value of Information from Horizontal Distributed Acoustic Sensing Compared to Multicompo- nent Geophones via Machine Learning Whitney J. Trainor-Guitton , SeaOwl Energy Services contracted to Total...

... as the target datasets in the experiments and find out that with only 10 labeled images from the target dataset, the model adapts very well and gives more accurate picking results compared with the plain transfer learning. To our best knowledge, this is the first work of using meta-learning in seismic image...

...: 1:50 PM Presentation Time: 1:50 PM Location: 351F Presentation Type: Oral upstream oil & gas manually-picked salt mask ground truth machine learning confidence map proceedings seg international exposition u-saltnet seismic image neural network salt body module interpretation...

...Deep learning for simultaneous seismic image super-resolution and denoising Jintao Li1, Xinming Wu1 and Zhanxuan Hu2 1School of Earth and Space Sciences, University of Science and Technology of China, 2Northwestern Polytechnical University. 64 64 64 64 1 SUMMARY 1 64 64 Maxpooling Concat 64 128 64...

...Deep learning for seismic image registration Arnab Dhara*, The University of Texas at Austin; Claudio Bagaini, Schlumberger Summary where and are the number of samples in the and direction. In general, 1 and 2 may not be related by only We developed a supervised machine learning technique to depth...

...Complete Sequence Stratigraphy from Seismic Optical Flow without Human Labeling Zhun Li* and Aria Abubakar, Schlumberger Summary have been adopted as a potential solution for automatic seismic image segmentation and horizon interpretation. Sequence stratigraphy is important to determine geological...

... re ectors various automatic methods have been proposed, most of them across faults. To deal with this issue, some methods remove fail to pick horizons across discontinuities such as faults and the faults in a seismic image (e.g., Luo and Hale, 2013; Wu noise. We propose a dynamic programming...

...Deep learning for characterizing paleokarst features in 3D seismic images Xinming Wu ,1, Shangsheng Yan1, Jie Qi2, and Hongliu Zeng3 1School of Earth and Space Sciences, University of Science and Technology of China; 2University of Oklahoma; 3Bureau of Economic Geology, University of Texas...

... Facies classification in seismic image using convolutional neural network (CNN) has gained great popularity for its high accuracy. But its accuracy with limited labelled dataset is affected due to changing viewpoints such as rotation. The attributes obtained by the scattering transform...

... ABSTRACT The three seismic image processing tasks of fault detection, structure-oriented smoothing with edge preserving, and slope estimation are related to each other and all involve analyzing seismic structural features. In conventional processing schemes, however, these three tasks...

... ABSTRACT Image-domain least-squares migration methods that explicitly compute the acquisition-migration system impulse response help to reveal the earth’s reflectivity by the deconvolution of these point-spread functions (PSFs) from the seismic image. However, their construction relies...

... ABSTRACT In this paper, we present an application of most advanced DL (Deep Learning) approaches, in characterizing subsurface salt body on seismic images. Nowadays, DL has been widely used in many industries and achieving tons of successful results, while it is pioneering work to explore...

... the seismic image. Stacking these weighted partial images over velocity provides us with a path-integral seismic diffraction image constructed using probability weights. We apply the method to a 2D field dataset from the Viking Graben. We find that the proposed approach creates diffraction images that better...