Performance Engineering for Deep Learning Adaptation of Seismic Processing Workflow

被引：0

作者：

Panda, Aniruddha ^{[1
]}

Chawdhary, Saurabh ^{[1
]}

Banerjee, Subhasis ^{[1
]}

Devarakota, Pandu ^{[2
]}

机构：

[1] Shell India Markets Pvt Ltd, Bangalore, Karnataka, India

[2] Shell Global Solut, Houston, TX USA

来源：

PROCEEDINGS OF THE 5TH JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE & MANAGEMENT OF DATA, CODS COMAD 2022 | 2022年

关键词：

Performance Engineering; Machine Learning / Deep Learning (ML/DL); Seismic Processing;

D O I：

10.1145/3493700.3493770

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the energy industry, high performance computing has long been a significant enabler for solving compute challenges. Seismic imaging, reservoir engineering, computational chemistry, CFD simulations, and many other large-scale challenges in the modelling and simulation space necessitate HPC resources to solve and expedite workflows. However, large scale data processing using Deep Learning (DL) techniques is yet to be exploited to its full potential by energy industry. There has recently been enough interest in the geophysics community to leverage the power of DL to make seismic processing and imaging workflows more efficient. In this tutorial, we first present a high level overview of the challenges and opportunities in seismic processing and imaging workflow, and propose an in-depth analysis of the performance engineering aspects of DL-based workflows.

引用

页码：342 / 343

页数：2