Like many people and companies around the world during these unprecedented times, we are exploring the opportunities, while navigating the challenges, associated with the migration online of many of our traditional activities, such as technical presentations and exhibitions.
CGG's global geoscience technologies enable you to build comprehensive earth models that support the discovery and responsible management of the Earth's natural resources. Our broad range of leading products and expert services help unlock the secrets of the earth through a variety of geoscience disciplines.
The EAGE website hosts our virtual technical presentations. If the dates/times don't fit your schedule, please feel free to contact us to request a personal meeting.
Deep Learning for Seismic Data Reconstruction: Opportunities and Challenges
2:00 PM CET Wednesday December 2
Machine Assisted Geophysics I
Natural and instrumental conditions during field seismic survey lead to noise and irregularities in acquired seismic data. In this work, we explore challenges and opportunities related to denoising and interpolation of seismic data by deep convolutional neural networks. In particular, we apply three network configurations to field data and match them with suitable applications. We show that U-Net is beneficial for denoising applications while adversarial generative networks (GAN) are superior in interpolation tasks. Enhanced interpolation capability of GANs, however, comes at cost of increased uncertainty in the results and we raise awareness about this observation. In the end, we consider the pitfalls of conventional metrics and outline the requirements for data-driven approaches to be suitable in production applications.
Understanding How a Deep Neural Network Architecture Choice Can Be Related to a Seismic Processing Task
5:00 PM CET Wednesday December 2
Machine Assisted Geophysics II
One of the many challenges in the way of the adoption of Deep Learning (DL) for seismic processing is the understanding of deep neural network (DNN) architecture and components with the associated underlying physics involved in a specific processing task. In this article, we study how some convolutional DNN architectures can be naturally suited to given processing tasks, helping the interpretability and opening the door to meaningful QCs. For instance, we show that the Unet architecture (Ronneberger et al., 2015) can naturally learn to “separate” the kinematics of seismic events from their amplitude variations and use both information efficiently; this is illustrated on the CIG (common image gathers) skeletonization (or picks probability computation) and muting task. We also illustrate that the Denet (Remez et al, 2017) architecture can naturally learn to decompose a “noise” model into meaningful complementary contributions, with the receiver deghosting from variable depth streamer data example.
It's about you, not just about the data. CGG can help you put data, analytics and machine learning to work to solve your geoscience and engineering challenges.
Minimize data infrastructure costs with a highly flexible, integrated data storage environment via CGG’s proprietary cloud infrastructure or Microsoft’s Azure.